© 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. 79261
    Prev
    Next
    INDEX
    Explanations

    County, census, Control, thrombosis, SønderjyskE, Harman

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

    text associated with software code and technical documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     ファ
    -0.68
    Randy
    -0.68
    公
    -0.66
     Sien
    -0.66
     Visser
    -0.66
    dow
    -0.65
     Schot
    -0.65
    一切
    -0.64
    himi
    -0.63
    空港
    -0.62
    POSITIVE LOGITS
    servant
    0.73
    jaan
    0.72
    uevo
    0.72
     Neuen
    0.69
    Shutter
    0.68
    фли
    0.68
    弐
    0.68
     hjäl
    0.67
     områ
    0.66
     servo
    0.66
    Activations Density 0.069%

    No Known Activations