© 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. 106845
    Prev
    Next
    INDEX
    Explanations

    code snippets and dates

    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
     Pixabay
    -0.80
     많
    -0.76
    ţie
    -0.74
    Sess
    -0.70
    liquez
    -0.68
     previous
    -0.68
     فرنسا
    -0.68
    Cerca
    -0.67
    inted
    -0.67
    </
    -0.67
    POSITIVE LOGITS
    publicPath
    0.84
    パイプ
    0.73
     mercury
    0.72
     Sunak
    0.71
    dtypes
    0.71
     sacerdotes
    0.71
     bodybuilding
    0.70
     valmist
    0.69
    Rider
    0.69
    taman
    0.69
    Activations Density 0.039%

    No Known Activations