© 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. 80624
    Prev
    Next
    INDEX
    Explanations

    report issues or results

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

    This neuron detects mentions of reporting or reports (e.g., “report,” “reported,” “reporting”).

    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
     и
    -2.03
    ↵↵
    -2.00
     will
    -1.89
     (
    -1.75
     I
    -1.66
    T
    -1.64
     و
    -1.62
    ги
    -1.62
     мы
    -1.59
    h
    -1.59
    POSITIVE LOGITS
     実例
    1.66
     participaron
    1.60
    ཫ
    1.55
     REPORTING
    1.53
    ほうが
    1.53
     Projektu
    1.53
    
    1.52
    
    1.50
     кількість
    1.49
     sarebbero
    1.48
    Activations Density 0.101%

    No Known Activations