© 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. 67143
    Prev
    Next
    INDEX
    Explanations

    mathematical structures and definitions

    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
     два
    -0.97
     отде
    -0.92
     direita
    -0.88
    iters
    -0.85
     گوشی
    -0.85
    倆
    -0.85
    iczne
    -0.84
    oane
    -0.84
    hews
    -0.84
    aliyet
    -0.84
    POSITIVE LOGITS
     any
    1.28
     with
    1.01
     simple
    0.97
     anybody
    0.93
     type
    0.92
     certainly
    0.91
    {?>
    0.91
    serialization
    0.89
    type
    0.89
    0.89
    Activations Density 0.070%

    No Known Activations