© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11691
    Prev
    Next
    INDEX
    Explanations

    multi-cultural expressions

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

    The neuron strongly activates on lines of shell-style commands or code diff hunks (e.g. echo statements, grep/build-log commands, and “+”/“-” prefixed patch lines).

    oai_token-act-pair · o4-miniTriggered 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
     *
    0.86
     ក
    0.67
     */
    0.64
     //
    0.61
    *
    0.61
     •
    0.59
        
    0.58
     /*
    0.58
     använd
    0.57
       
    0.56
    POSITIVE LOGITS
    ᵔ
    0.59
    实的
    0.55
    odor
    0.54
    textures
    0.54
    recognizable
    0.53
    λέ
    0.53
    ---------------+
    0.53
    罫
    0.52
     عبدال
    0.51
     відповід
    0.50
    Activations Density 0.002%

    No Known Activations