© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129176
    Prev
    Next
    INDEX
    Explanations

    hands on

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

    The neuron strongly activates on the word “hands” (including in hands-on, hands-up, hands-off, etc.).

    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
    3
    -1.87
    7
    -1.82
     would
    -1.70
     of
    -1.57
    6
    -1.52
    4
    -1.44
    1
    -1.36
    蠵
    -1.35
    ="")
    -1.32
    鮨
    -1.31
    POSITIVE LOGITS
    蓠
    1.55
    俺は
    1.53
     tht
    1.40
    𝐷
    1.40
    <bos>
    1.38
    やってる
    1.38
    さぎ
    1.37
     һ
    1.36
     XXI
    1.35
    صیل
    1.34
    Activations Density 0.021%

    No Known Activations