© 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. 118865
    Prev
    Next
    INDEX
    Explanations

    exclamation of relief

    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
     malen
    -0.90
     merawat
    -0.82
     lyk
    -0.75
     postale
    -0.73
    линг
    -0.73
     perawatan
    -0.73
     reise
    -0.71
     uten
    -0.71
     mulig
    -0.71
     trésor
    -0.71
    POSITIVE LOGITS
    Phew
    3.77
    Whew
    3.75
     Whe
    3.28
    whe
    3.19
    phe
    3.11
     whe
    2.86
    WHE
    2.52
     WHE
    2.48
    PHE
    2.45
     PHE
    2.27
    Activations Density 0.022%

    No Known Activations