© 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. 104597
    Prev
    Next
    INDEX
    Explanations

    module identifiers and documentation

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

    the word "module" in programming contexts, especially in file paths, import statements, and technical documentation.

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

    The neuron fires on occurrences of the word “module” (especially in code identifiers or declarations).

    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
    
    -2.50
     unſ
    -2.19
     vorsichtig
    -2.02
     bahwa
    -1.95
     wykonane
    -1.94
    ᾐ
    -1.93
     広場
    -1.90
    ,  
    -1.88
    wakili
    -1.87
    
    -1.86
    POSITIVE LOGITS
    (
    2.77
    \
    2.72
        
    2.41
    In
    2.36
     esteemed
    2.27
     AND
    2.11
    am
    2.11
     хорошем
    2.02
    している
    2.00
    –
    1.99
    Activations Density 0.036%

    No Known Activations