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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72974
    Prev
    Next
    INDEX
    Explanations

    body parts

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

    references to parts of the face or head, particularly in violent or medical 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_10/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
    1
    -1.80
    ]
    -1.75
    ’
    -1.67
    (
    -1.66
     that
    -1.62
     there
    -1.57
    '
    -1.48
    ;
    -1.34
    {
    -1.31
    [
    -1.30
    POSITIVE LOGITS
     剧照
    1.80
     regata
    1.56
     違い
    1.55
    \|_{\
    1.48
    ας
    1.48
    erintah
    1.48
     for
    1.47
     of
    1.47
    旒
    1.44
    
    1.41
    Activations Density 0.009%

    No Known Activations