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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101697
    Prev
    Next
    INDEX
    Explanations

    script related actions and context

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

    the word "script" in various contexts.

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

    This neuron activates on occurrences of the word “script” (and its morphological variants) in the text.

    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
    s
    -2.52
    6
    -2.13
    
    -1.92
                
    -1.86
    2
    -1.84
    橚
    -1.84
    4
    -1.84
    无论是
    -1.83
    鵟
    -1.82
    ↵↵
    -1.77
    POSITIVE LOGITS
    皚
    2.00
    뮈
    1.97
    戕
    1.96
    _));
    1.91
    Certainly
    1.91
    sizeCache
    1.87
     Empieza
    1.83
     desmotiv
    1.80
     instability
    1.80
    divarius
    1.77
    Activations Density 0.016%

    No Known Activations