© 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. 78341
    Prev
    Next
    INDEX
    Explanations

    import statements; python encoding

    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
    æd
    -0.82
     pain
    -0.69
     réguli
    -0.68
     recognition
    -0.67
    大全
    -0.67
     Standards
    -0.66
    Waypoint
    -0.66
     standards
    -0.65
     Flag
    -0.65
     wä
    -0.65
    POSITIVE LOGITS
    argc
    0.84
    <0xE0>
    0.79
     Cuc
    0.74
     розмі
    0.74
    ዳ
    0.68
     Sixt
    0.67
     медици
    0.67
    렌
    0.66
    Pane
    0.66
     Apertura
    0.66
    Activations Density 0.054%

    No Known Activations