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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101664
    Prev
    Next
    INDEX
    Explanations

    code components namespace

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

    backslashes used as namespace separators in PHP code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     with
    -2.16
    {
    -2.06
     in
    -2.00
    );
    -1.92
    '
    -1.85
     when
    -1.77
    .
    -1.65
    ">
    -1.59
     on
    -1.58
     usual
    -1.56
    POSITIVE LOGITS
    颪
    2.03
    湉
    1.96
     ||
    1.92
    \%
    1.91
    mirante
    1.87
    蟶
    1.87
    𓆟
    1.83
    ︲
    1.81
    ientras
    1.80
     élevé
    1.78
    Activations Density 0.017%

    No Known Activations