© 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. 83870
    Prev
    Next
    INDEX
    Explanations

    choreographer and choreography

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

    The neuron responds to words related to choreography (e.g., “choreography,” “choreographed,” “choreographer”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    d
    -2.59
    s
    -2.20
    </h3>
    -2.20
    c
    -2.09
    de
    -2.03
     или
    -1.99
    н
    -1.96
    or
    -1.93
    es
    -1.92
    will
    -1.89
    POSITIVE LOGITS
    婓
    2.11
    愎
    2.06
    </sup>
    2.05
    ༵
    2.03
    ܖ
    2.03
    ᨆ
    1.95
    糨
    1.95
     caros
    1.91
    鉝
    1.89
     olhando
    1.88
    Activations Density 0.002%

    No Known Activations