© 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. 34-GEMMASCOPE-RES-131K
    7. 813
    Prev
    Next
    INDEX
    Explanations

    final rule

    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
    ENCIES
    -0.77
     zkou
    -0.76
    玩笑
    -0.73
    huriyet
    -0.73
     Можно
    -0.70
    ੌ
    -0.69
    垚
    -0.69
     voluntad
    -0.67
    왜
    -0.67
     øns
    -0.67
    POSITIVE LOGITS
     rule
    2.56
    rule
    1.94
     Rule
    1.90
    Rule
    1.69
     rules
    1.61
     RULE
    1.50
    final
    1.43
     final
    1.41
     правило
    1.35
    规则
    1.34
    Activations Density 0.036%

    No Known Activations