© 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. 58108
    Prev
    Next
    INDEX
    Explanations

    css bootstrap ico

    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
    -
    -2.08
     it
    -2.03
     ‘
    -1.87
    :
    -1.73
     if
    -1.69
     behauptet
    -1.67
    _
    -1.65
    d
    -1.64
     four
    -1.63
     but
    -1.59
    POSITIVE LOGITS
     okazji
    1.59
    Bjs
    1.57
    ܴ
    1.56
     goûts
    1.55
     poussière
    1.55
     starte
    1.55
     épices
    1.53
    錞
    1.53
     Secretario
    1.52
     flotte
    1.52
    Activations Density 0.022%

    No Known Activations