© 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. 10-GEMMASCOPE-RES-131K
    7. 15585
    Prev
    Next
    INDEX
    Explanations

    benzodiazepines, Heinz, Bianca, Katrina, Acer, Kras

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

    chemical compounds related to benzodiazepines.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ;
    -3.45
    {
    -3.39
    '
    -3.23
    ?”
    -3.23
    ra
    -2.98
    }$
    -2.97
    ");
    -2.97
    ri
    -2.97
    的
    -2.95
    ){
    -2.91
    POSITIVE LOGITS
    沨
    3.08
    三個
    2.94
    仨
    2.72
    遠い
    2.64
    嵓
    2.63
    不愿
    2.59
    どうやって
    2.56
    有过
    2.55
    没能
    2.53
    کاربرد
    2.50
    Activations Density 0.014%

    No Known Activations