© 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. 22-GEMMASCOPE-RES-131K
    7. 32590
    Prev
    Next
    INDEX
    Explanations

    unsigned int parameters

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    LLO
    -0.84
     アメリカ
    -0.80
     dangers
    -0.78
     Wählen
    -0.76
     deko
    -0.74
     Особенно
    -0.73
     spiele
    -0.73
    havn
    -0.72
     aproape
    -0.72
    endPoint
    -0.72
    POSITIVE LOGITS
    Похо
    0.82
     suficiente
    0.80
    uncias
    0.77
    inoma
    0.77
     Cells
    0.76
     вважа
    0.75
    outState
    0.74
    metres
    0.73
    に行く
    0.73
     ngh
    0.73
    Activations Density 0.046%

    No Known Activations