© 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. 3584
    Prev
    Next
    INDEX
    Explanations

    spotted fever

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

    names of people, particularly surnames or surnames in combination with first names.

    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
    psz
    -0.84
    VV
    -0.77
     Celestial
    -0.74
     liệu
    -0.73
    kao
    -0.71
    献
    -0.71
    gero
    -0.70
     bodyParser
    -0.69
     اهمیت
    -0.69
     Lay
    -0.69
    POSITIVE LOGITS
    冨
    0.81
     minimized
    0.78
     neuesten
    0.77
     brom
    0.76
    uito
    0.76
    ereka
    0.71
     minimization
    0.71
    毎回
    0.70
     zentralen
    0.70
    openModal
    0.69
    Activations Density 0.034%

    No Known Activations