© 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. 113272
    Prev
    Next
    INDEX
    Explanations

    `*`, `[@`, `(`, `)`, `[`

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

    italicized variables or symbols in scientific and technical documents.

    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
     -
    -2.06
     slight
    -1.94
    Они
    -1.92
    獁
    -1.89
     varandra
    -1.89
     båda
    -1.84
    ,
    -1.77
    Еще
    -1.77
    ített
    -1.75
    Другие
    -1.74
    POSITIVE LOGITS
     to
    2.45
    mpagne
    2.05
     amd
    1.98
    と言えば
    1.91
    reathe
    1.91
     naturalmente
    1.87
    といえば
    1.84
    ౮
    1.80
    bugging
    1.80
    唯有
    1.79
    Activations Density 0.003%

    No Known Activations