© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3360
    Prev
    Next
    INDEX
    Explanations

    pprof

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

    The neuron flags numeric tokens, particularly multi‐digit numbers (often with decimal points).

    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_24_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
     Tài
    0.56
    aparikkh
    0.52
    <0xA0>
    0.50
    auteur
    0.50
    élix
    0.49
    ObjectMapper
    0.49
    ärt
    0.48
    ਮ
    0.47
     Bắc
    0.47
    unoscut
    0.47
    POSITIVE LOGITS
     diterapkan
    0.60
     dipilih
    0.59
     ditampilkan
    0.58
     visualisation
    0.57
     votre
    0.56
     dengan
    0.55
     visualizations
    0.55
     sample
    0.54
     visualization
    0.54
     chosen
    0.54
    Activations Density 0.011%

    No Known Activations