© 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. 85588
    Prev
    Next
    INDEX
    Explanations

    names associated with surnames or titles

    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
     The
    -2.81
    </h4>
    -2.53
    
    -2.52
    찮
    -2.50
    pecabe
    -2.45
     they
    -2.39
     Our
    -2.25
     Ortsteil
    -2.23
    \\
    -2.22
    ,...
    -2.22
    POSITIVE LOGITS
    </i>
    3.69
    呖
    3.06
    之为
    2.50
    獴
    2.38
    ܜ
    2.30
     necessitates
    2.25
    \
    2.25
    晙
    2.14
    𐄁
    2.11
    TEL
    2.09
    Activations Density 0.015%

    No Known Activations