© 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. 10-GEMMASCOPE-RES-131K
    7. 10448
    Prev
    Next
    INDEX
    Explanations

    in ways

    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_10/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
    ྂ
    -1.65
    Ỗ
    -1.56
    是由
    -1.56
    
    -1.45
    失踪
    -1.42
     exclusivas
    -1.39
     químicas
    -1.38
    孓
    -1.37
    singer
    -1.37
     us
    -1.36
    POSITIVE LOGITS
    <td>
    1.82
    on
    1.73
    AutoresizingMask
    1.72
    “
    1.70
     -
    1.67
    v
    1.66
    ons
    1.56
    «
    1.55
     på
    1.52
    ?
    1.52
    Activations Density 0.017%

    No Known Activations