© 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. 83960
    Prev
    Next
    INDEX
    Explanations

    fileID:

    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
     shown
    -1.66
    taglio
    -1.48
    fillment
    -1.45
    versies
    -1.44
    endimento
    -1.43
    ichtete
    -1.40
    の為
    -1.38
     possa
    -1.38
    aneers
    -1.38
     pouces
    -1.37
    POSITIVE LOGITS
    也會
    1.95
    也会
    1.73
    0
    1.57
     them
    1.54
     these
    1.48
    4
    1.47
    f
    1.47
    Beskrivning
    1.42
    anglicky
    1.39
     パッケージ
    1.35
    Activations Density 0.116%

    No Known Activations