© 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. 8010
    Prev
    Next
    INDEX
    Explanations

    food, drinks, and fashion

    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
     and
    -2.38
     \
    -1.98
    ).
    -1.77
     fled
    -1.71
    APPENDICES
    -1.62
    </h2>
    -1.59
    潆
    -1.54
          
    -1.49
     bởi
    -1.49
     gosta
    -1.48
    POSITIVE LOGITS
     mengha
    1.98
     pasajeros
    1.82
     unrival
    1.80
    萏
    1.77
     bañera
    1.76
     rých
    1.74
    zuf
    1.73
     angebra
    1.73
    熥
    1.73
     potře
    1.71
    Activations Density 0.006%

    No Known Activations