© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12172
    Prev
    Next
    INDEX
    Explanations

    kotlin null safety and programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is triggered by numeric tokens—especially detailed specification values (e.g. hardware benchmarks or measurements with digits and decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to Adreno GPU models with specific numbers (like Adreno 505, 530, 225).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of smartphone graphics hardware specifications, particularly mobile GPU model names and related graphics performance details.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    रावर
    0.59
     valuation
    0.57
     enn
    0.56
     Lakeside
    0.56
     sequencing
    0.55
     Metcalf
    0.55
    ledu
    0.54
     लाभदायक
    0.52
     Milling
    0.52
     vibhav
    0.52
    POSITIVE LOGITS
    !!.
    0.71
    toInt
    0.54
    let
    0.54
     нейтро
    0.54
     Let
    0.53
    !!)
    0.53
    Let
    0.51
    Ꮙ
    0.51
    ҝ
    0.51
    !!
    0.51
    Activations Density 0.024%

    No Known Activations