© 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. 34-GEMMASCOPE-RES-131K
    7. 117262
    Prev
    Next
    INDEX
    Explanations

    code and metadata

    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_34/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
     into
    -0.76
    喹
    -0.75
     psychology
    -0.69
     tante
    -0.68
     Kuhn
    -0.68
     tuya
    -0.68
    ").
    -0.67
     omnia
    -0.66
     vmax
    -0.66
     Sangu
    -0.65
    POSITIVE LOGITS
     Timber
    0.68
     وجه
    0.67
    })(
    0.66
    rill
    0.66
    uawei
    0.66
    ReadKey
    0.66
     المنطقة
    0.65
    dighet
    0.65
     Green
    0.65
     Innovation
    0.65
    Activations Density 0.096%

    No Known Activations