© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40837
    Prev
    Next
    INDEX
    Explanations

    hinge, fold, and closure mechanisms

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

    The neuron fires on technical terms for mechanical motions—especially fold-, hinge-, pivot-, open/close-type verbs—used in product or patent descriptions.

    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
    がこの
    -1.41
    のデザイン
    -1.32
     boneco
    -1.20
    はこの
    -1.20
     to
    -1.19
    鷭
    -1.19
     menino
    -1.16
    這個
    -1.16
     ナイロン
    -1.16
    那些
    -1.14
    POSITIVE LOGITS
     from
    1.47
     out
    1.37
     two
    1.31
     with
    1.27
    $-.
    1.24
     on
    1.21
    .’
    1.20
    れたら
    1.16
     our
    1.15
     With
    1.14
    Activations Density 0.063%

    No Known Activations