© 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. 71610
    Prev
    Next
    INDEX
    Explanations

    into a specific form

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    webtoken
    -1.59
    in
    -1.58
    十几
    -1.56
    狁
    -1.52
    wiada
    -1.52
    Www
    -1.51
     которы
    -1.50
    怼
    -1.45
    ries
    -1.43
    erie
    -1.42
    POSITIVE LOGITS
    </strong>
    1.95
     установка
    1.74
    ↵
    1.63
     séjours
    1.57
     trouvez
    1.57
     ‘
    1.55
    </h1>
    1.54
     a
    1.53
     seguintes
    1.53
     女人
    1.52
    Activations Density 0.016%

    No Known Activations