© 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. 9231
    Prev
    Next
    INDEX
    Explanations

    punctuation and specifiers

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

    This neuron strongly activates on tokens that appear in website navigation bars or section‐heading menus (e.g. “Links,” “Marketing,” “Review,” “Terms of,” “Capital,” “More,” etc.). It’s effectively detecting site‐navigation/section‐label text.

    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
    K
    0.78
    /
    0.75
     (
    0.74
    -
    0.68
    D
    0.65
    +(
    0.64
    J
    0.63
    （
    0.63
    ᆸ
    0.63
    (
    0.62
    POSITIVE LOGITS
     nigeria
    0.90
     england
    0.89
     méxico
    0.88
    ?
    0.84
     samoglas
    0.82
    :.
    0.79
     williams
    0.79
     california
    0.79
     significado
    0.77
     allah
    0.76
    Activations Density 1.252%

    No Known Activations