© 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. 69797
    Prev
    Next
    INDEX
    Explanations

    operate, operating, operated

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

    The neuron activates on verbs related to operating or actuating (e.g., “operate,” “operates,” “operated,” “operating,” “actuate,” “actuated”).

    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
     
    -1.98
    '
    -1.88
     '
    -1.57
     there
    -1.55
     have
    -1.54
     they
    -1.44
     セン
    -1.38
     '?'
    -1.37
    <bos>
    -1.36
    『
    -1.32
    POSITIVE LOGITS
    涠
    1.91
    
    1.73
    𝒛
    1.72
    䤀
    1.67
    abetta
    1.66
     oblivious
    1.60
    鎳
    1.54
    με
    1.53
    它们
    1.52
     acuarela
    1.48
    Activations Density 0.109%

    No Known Activations