© 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. 22-GEMMASCOPE-RES-131K
    7. 66126
    Prev
    Next
    INDEX
    Explanations

    divided by / passing through

    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_22/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
    használ
    -0.91
    也许
    -0.89
     acabamento
    -0.88
    gucigalpa
    -0.85
     duże
    -0.84
     duży
    -0.83
     Теперь
    -0.82
     löst
    -0.81
     poderão
    -0.81
     dédiée
    -0.81
    POSITIVE LOGITS
    Orchid
    0.96
     finir
    0.84
    ologica
    0.82
     éta
    0.82
     raiſ
    0.81
    ologia
    0.79
    Ond
    0.79
     合金
    0.79
     rounding
    0.78
    Nino
    0.78
    Activations Density 0.003%

    No Known Activations