© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38341
    Prev
    Next
    INDEX
    Explanations

    in, at, among

    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
    Negative Logits
    咐
    -1.97
    tionally
    -1.88
    😵
    -1.82
    ~~~~~~~
    -1.81
     asesinado
    -1.80
     XXXV
    -1.77
    <%@
    -1.75
    ;'>
    -1.74
    😤
    -1.73
    塒
    -1.72
    POSITIVE LOGITS
     那
    1.88
     “
    1.65
     但是
    1.56
     但
    1.52
    archiwizowane
    1.52
     \
    1.47
    </strong>
    1.47
     only
    1.43
    震惊
    1.43
     таких
    1.41
    Activations Density 0.006%

    No Known Activations