© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38981
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
     torchvision
    -1.00
    สูง
    -0.97
    曲は
    -0.96
    cheduled
    -0.96
    Pozdrawiam
    -0.93
     widać
    -0.92
    μων
    -0.92
    godic
    -0.92
    pozdrawiam
    -0.90
    paigns
    -0.90
    POSITIVE LOGITS
    程度上
    0.98
     Clippers
    0.96
     -$
    0.95
    ないです
    0.94
     criteria
    0.94
    原理
    0.93
     любой
    0.93
     требу
    0.93
     formed
    0.93
     распо
    0.92
    Activations Density 0.034%

    No Known Activations