© 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. 109862
    Prev
    Next
    INDEX
    Explanations

    rule definition

    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
    菸
    -0.69
     appar
    -0.69
    
    -0.68
     đời
    -0.67
    verwaltung
    -0.66
     Lom
    -0.66
     Pao
    -0.66
    稲田
    -0.66
    対戦
    -0.66
     SUP
    -0.66
    POSITIVE LOGITS
     rule
    1.68
    rule
    1.52
     Rule
    1.46
     rules
    1.46
    Rule
    1.42
     Rules
    1.34
    Rules
    1.32
    RULE
    1.32
     RULE
    1.21
    rules
    1.16
    Activations Density 0.078%

    No Known Activations