© 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. 16656
    Prev
    Next
    INDEX
    Explanations

    grid positions, maze paths, or objects

    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
    ofing
    -1.07
     what
    -0.98
    viembre
    -0.95
    andingan
    -0.94
    ufige
    -0.93
    lanması
    -0.93
    liski
    -0.91
    бов
    -0.90
    dians
    -0.90
     encantó
    -0.90
    POSITIVE LOGITS
     формате
    0.93
     space
    0.88
     teils
    0.87
     хорошем
    0.85
     hinsichtlich
    0.85
    方針
    0.83
     iub
    0.82
    代わりに
    0.81
     status
    0.81
     walls
    0.79
    Activations Density 0.013%

    No Known Activations