© 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. 104439
    Prev
    Next
    INDEX
    Explanations

    movement and disorders

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

    The neuron detects the word "movement" and related concepts in text, particularly in contexts about physical mobility or bodily functions.

    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
    (
    -2.95
    *
    -2.92
    of
    -2.70
    ar
    -2.58
    \
    -2.48
    O
    -2.30
    et
    -2.23
    [
    -2.19
     marvel
    -2.14
    ]
    -2.13
    POSITIVE LOGITS
    趼
    3.27
    蛱
    2.75
    .
    2.53
    薹
    2.41
    enfone
    2.39
    ୪
    2.38
    谞
    2.38
    𐄁
    2.36
    攫
    2.36
     accessing
    2.36
    Activations Density 0.007%

    No Known Activations