© 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. 84428
    Prev
    Next
    INDEX
    Explanations

    code type checks

    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
    ."
    -2.17
    o
    -2.11
    秕
    -2.09
    猡
    -2.08
     Even
    -2.06
     It
    -2.00
     glede
    -1.98
     He
    -1.91
    );
    -1.91
    ).
    -1.91
    POSITIVE LOGITS
     nhưng
    2.38
    новь
    2.27
    ی
    2.25
    暃
    2.16
    their
    2.16
    の人が
    2.14
    あんな
    2.13
    ⇴
    2.13
     esche
    2.13
    乀
    2.11
    Activations Density 0.001%

    No Known Activations