© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130016
    Prev
    Next
    INDEX
    Explanations

    PRAGMA, const, package, struct

    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
     to
    -1.93
     
    -1.88
    E
    -1.77
     A
    -1.65
     a
    -1.63
    A
    -1.63
     T
    -1.63
     P
    -1.55
     acidente
    -1.52
    C
    -1.52
    POSITIVE LOGITS
    </h3>
    2.30
     zoude
    2.03
    鄚
    1.84
     tamu
    1.83
     houſe
    1.82
    </h4>
    1.79
     fendi
    1.78
     kutu
    1.77
     水墨
    1.77
     jenner
    1.76
    Activations Density 0.002%

    No Known Activations