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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39784
    Prev
    Next
    INDEX
    Explanations

    mechanical clutches and transmissions

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

    The main thing this neuron does is detect occurrences of the word “clutch” (especially in technical or mechanical contexts).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    蛧
    -2.44
    燦
    -2.36
     Какие
    -2.33
    쐈
    -2.31
    लाई
    -2.31
     Некоторые
    -2.27
    粄
    -2.25
     eſſ
    -2.22
    粢
    -2.19
    鉺
    -2.19
    POSITIVE LOGITS
    \
    2.47
    螂
    2.42
    i
    2.42
    and
    2.41
    And
    2.38
     और
    2.31
     AND
    2.30
    不会
    2.28
    ))
    2.25
    ...)
    2.23
    Activations Density 0.003%

    No Known Activations