© 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. 34-GEMMASCOPE-RES-131K
    7. 73393
    Prev
    Next
    INDEX
    Explanations

    Dr. Quinn Medicine Woman, Recurrence

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

    proper nouns and titles, particularly related to media and entertainment.

    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
    setUse
    -0.80
     Fairy
    -0.80
    lite
    -0.77
     fairy
    -0.76
    NBS
    -0.76
    motive
    -0.75
    LikeLike
    -0.74
    WN
    -0.74
    ntgen
    -0.73
    lectric
    -0.73
    POSITIVE LOGITS
     MST
    0.86
     mst
    0.82
     Servo
    0.80
    arture
    0.76
     MOVIE
    0.71
     jumpsuit
    0.71
    MST
    0.70
    Servo
    0.70
    ertos
    0.69
    🥯
    0.69
    Activations Density 0.011%

    No Known Activations