© 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. 65846
    Prev
    Next
    INDEX
    Explanations

    stretch or stretchy

    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
     comprised
    -2.11
     中身
    -1.98
    Ꮉ
    -1.97
     メニュー
    -1.92
    髣
    -1.85
    迨
    -1.84
    UGHTER
    -1.80
     ポーズ
    -1.79
     ネタバレ
    -1.77
     about
    -1.73
    POSITIVE LOGITS
    ",
    2.16
    [
    1.93
    ',
    1.92
    ers
    1.88
     ولی
    1.84
    3
    1.82
    ſelf
    1.81
    、
    1.81
    r
    1.80
    ."
    1.70
    Activations Density 0.004%

    No Known Activations