© 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. 102989
    Prev
    Next
    INDEX
    Explanations

    technical modules

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

    the word "module" in technical patent and documentation contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron activates on the word “module.”

    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
    
    -2.81
     ausein
    -2.58
     unſ
    -2.56
     vorsichtig
    -2.53
    ㌘
    -2.38
     geladeira
    -2.36
     広場
    -2.34
    ₶
    -2.33
     個室
    -2.27
     стоковые
    -2.25
    POSITIVE LOGITS
    In
    3.53
    \
    2.97
     も
    2.92
    м
    2.72
     If
    2.63
    嫆
    2.59
    It
    2.55
    ありますが
    2.52
    If
    2.48
     esteemed
    2.47
    Activations Density 0.017%

    No Known Activations