© 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. 22178
    Prev
    Next
    INDEX
    Explanations

    fabric types, names, places

    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
    ↵↵
    -2.81
    \
    -2.69
                    
    -2.67
    );
    -2.36
     Of
    -2.33
    GEBURTS
    -2.22
     flurry
    -2.16
     Incidentally
    -2.14
    us
    -2.05
    ⡪
    -2.03
    POSITIVE LOGITS
    eſt
    2.28
    Semitism
    2.17
    '
    2.16
     faſt
    2.11
    apatalk
    2.11
    ꪀ
    2.08
    牒
    2.02
    heureusement
    1.98
     χρησιμοποι
    1.94
     democrá
    1.91
    Activations Density 0.003%

    No Known Activations