© 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. 62590
    Prev
    Next
    INDEX
    Explanations

    assay, population, service, flag, test

    np_acts-logits-general · gemini-2.5-flash-lite

    HTML and programming code elements like brackets, tags, and programming syntax.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    zana
    -0.74
     Partei
    -0.74
    紮
    -0.68
    brews
    -0.67
    uuuuu
    -0.67
    ༼
    -0.66
    stol
    -0.66
    bear
    -0.66
    raiz
    -0.66
    madu
    -0.65
    POSITIVE LOGITS
    満た
    0.66
    šech
    0.63
    Ги
    0.63
     SIG
    0.62
     audited
    0.62
    ći
    0.61
    Producción
    0.61
    اة
    0.61
     Hatton
    0.61
     GCC
    0.60
    Activations Density 0.068%

    No Known Activations