© 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. 74622
    Prev
    Next
    INDEX
    Explanations

    with [noun phrase]

    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
    ᨆ
    -1.96
    轳
    -1.92
    鸶
    -1.87
    kede
    -1.77
    蓊
    -1.76
    
    -1.73
    荜
    -1.72
    𐬹
    -1.71
     CONCEP
    -1.70
     PÉ
    -1.70
    POSITIVE LOGITS
    '
    2.48
    "
    2.27
    [
    1.94
    The
    1.91
    .
    1.86
    <b>
    1.77
    \
    1.71
    --
    1.69
    :
    1.69
     Another
    1.68
    Activations Density 0.148%

    No Known Activations