© 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. 73103
    Prev
    Next
    INDEX
    Explanations

    expression

    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
     of
    -2.48
     now
    -1.72
    注意事
    -1.58
    usercontent
    -1.57
     tuo
    -1.56
    幛
    -1.53
     rostros
    -1.52
     этому
    -1.45
    楦
    -1.45
     a
    -1.41
    POSITIVE LOGITS
    .
    1.79
     limpiar
    1.46
     invitar
    1.45
     in
    1.41
     ее
    1.34
     Another
    1.34
     rebaj
    1.34
     Autres
    1.33
     sostener
    1.32
     Erfüllung
    1.31
    Activations Density 0.326%

    No Known Activations