Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8639
    Prev
    Next
    INDEX
    Explanations

    Richard Bennett

    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
    OGUE
    -0.74
     вдруг
    -0.74
     almost
    -0.73
     Pte
    -0.71
    𝟏
    -0.71
    攻擊
    -0.71
     humility
    -0.69
     whose
    -0.69
    ImagePath
    -0.69
    قامة
    -0.69
    POSITIVE LOGITS
    FTC
    0.96
     スカート
    0.82
    tutorial
    0.81
     ‌
    0.81
    ControllerAdvice
    0.81
     ./
    0.80
    Thesis
    0.78
    thesis
    0.78
    tutorials
    0.78
    ఝ
    0.77
    Activations Density 0.015%

    No Known Activations