© 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. 34-GEMMASCOPE-RES-131K
    7. 3475
    Prev
    Next
    INDEX
    Explanations

    file system paths and URLs

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    poli
    -0.76
     kế
    -0.75
    hit
    -0.68
    SetTitle
    -0.68
     brevis
    -0.67
     Netherlands
    -0.67
    iran
    -0.66
     bore
    -0.64
    bor
    -0.64
     Hit
    -0.63
    POSITIVE LOGITS
    Fru
    0.76
     bolsa
    0.75
    Sola
    0.74
    selections
    0.73
    чника
    0.71
    rdı
    0.71
     אז
    0.70
     app
    0.69
     selectivity
    0.69
    Geometric
    0.68
    Activations Density 0.059%

    No Known Activations