© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39809
    Prev
    Next
    INDEX
    Explanations

    programming interface and class 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_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
    Two
    -2.28
    汌
    -2.27
     brilliant
    -2.25
    了一
    -2.23
    Another
    -2.22
     steadfast
    -2.19
    ;
    -2.13
    But
    -2.09
     talented
    -2.08
    地说道
    -2.06
    POSITIVE LOGITS
    or
    2.34
    蹰
    2.20
    )":
    2.17
    茈
    2.14
    鳐
    2.09
    꿩
    2.09
    
    2.08
    рного
    2.06
    癭
    2.06
    ⸫
    2.05
    Activations Density 0.003%

    No Known Activations