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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110472
    Prev
    Next
    INDEX
    Explanations

    dictate, dictation, dictator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    чайно
    -0.83
    ANGER
    -0.77
     Thales
    -0.73
    числи
    -0.73
     Goya
    -0.72
    defin
    -0.71
     Magazines
    -0.71
    PPI
    -0.70
     pertur
    -0.69
     refinery
    -0.69
    POSITIVE LOGITS
     dictate
    4.59
     dict
    4.59
    dict
    4.44
     dictated
    4.44
     dictation
    4.31
     Dict
    4.13
    Dict
    3.94
     dictates
    3.73
     dictator
    2.97
    DICT
    2.92
    Activations Density 0.056%

    No Known Activations