© 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. 62891
    Prev
    Next
    INDEX
    Explanations

    namespace xml json http

    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
     this
    -1.02
     what
    -0.93
     during
    -0.84
    本作
    -0.83
     long
    -0.82
     горе
    -0.81
    ится
    -0.78
    $-
    -0.75
     stylish
    -0.75
     came
    -0.75
    POSITIVE LOGITS
     despla
    0.95
    ofür
    0.94
     трени
    0.92
     encor
    0.91
     mą
    0.89
    achieve
    0.87
    年纪
    0.85
    wände
    0.85
    internal
    0.84
    kön
    0.84
    Activations Density 0.001%

    No Known Activations