© 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. 101307
    Prev
    Next
    INDEX
    Explanations

    bass guitar

    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
    谖
    -3.41
    
    -3.20
     باسلام
    -2.84
    彀
    -2.84
    緜
    -2.77
    腚
    -2.73
     笔画
    -2.66
    诹
    -2.64
    縂
    -2.64
    逖
    -2.63
    POSITIVE LOGITS
    A
    2.88
    𓋼
    2.63
    ときに
    2.61
    e
    2.45
    four
    2.44
     {}));
    2.39
    to
    2.39
    刳
    2.34
    主に
    2.33
    鸰
    2.30
    Activations Density 0.003%

    No Known Activations