© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128733
    Prev
    Next
    INDEX
    Explanations

    words starting with Ag

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

    The neuron is a detector for the standalone token “Ag,” i.e. occurrences of the two‐letter string Ag as its own token.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    厹
    -3.00
    懨
    -2.94
    豋
    -2.89
    犼
    -2.88
     OGSÅ
    -2.86
    ୪
    -2.58
     podendo
    -2.56
     pescoço
    -2.56
    ’;
    -2.56
    騭
    -2.55
    POSITIVE LOGITS
    *
    3.17
    >
    2.72
     ,
    2.67
    -
    2.66
     was
    2.64
    u
    2.42
    --
    2.39
    %
    2.36
    [
    2.36
     you
    2.36
    Activations Density 0.008%

    No Known Activations