© 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. 110423
    Prev
    Next
    INDEX
    Explanations

    testing and assertions

    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
    ТО
    -0.83
    س
    -0.81
    ع
    -0.80
    ठी
    -0.77
    AnchorStyles
    -0.76
     der
    -0.75
    조
    -0.74
     Hate
    -0.73
    обла
    -0.73
     Mather
    -0.72
    POSITIVE LOGITS
    參考
    0.82
    共演
    0.76
    Rüyada
    0.76
     spezi
    0.74
     faça
    0.73
     target
    0.73
     ベン
    0.73
     dividends
    0.73
     vizsg
    0.72
     HEC
    0.72
    Activations Density 0.002%

    No Known Activations