© 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. 14912
    Prev
    Next
    INDEX
    Explanations

    Wolfe, Jud, judoka, STAT, Kip

    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
     Both
    -3.17
    \
    -2.98
     coveted
    -2.88
     Like
    -2.81
     freaking
    -2.78
     riveting
    -2.70
     newfound
    -2.69
     Until
    -2.66
    接下来的
    -2.64
     freakin
    -2.58
    POSITIVE LOGITS
     ersche
    2.94
    所以我
    2.56
    </td>
    2.50
     nothwendig
    2.38
     bezw
    2.31
     gewiß
    2.30
    nly
    2.23
     cadeiras
    2.23
     vnnd
    2.22
     fotografias
    2.14
    Activations Density 0.007%

    No Known Activations