© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33973
    Prev
    Next
    INDEX
    Explanations

    menu buttons, Bell Aliant, oil yield, cardiovascular complications, magnetic ordering, drop attacks, adult tissue, line extensions

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

    brand and product names in technical contexts.

    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_22/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
     coq
    -1.02
     lança
    -0.98
     Barbecue
    -0.96
     levi
    -0.96
     Promotes
    -0.95
     concorda
    -0.94
     Hashtag
    -0.93
    有些
    -0.93
     vanta
    -0.93
     cloche
    -0.93
    POSITIVE LOGITS
    OOTDTY
    0.89
    帐
    0.88
     helemaal
    0.87
    Witnesses
    0.86
    %;
    0.86
    جمعیت
    0.86
     hatten
    0.85
    deki
    0.85
     Vorstand
    0.84
     čierna
    0.83
    Activations Density 0.100%

    No Known Activations