© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45222
    Prev
    Next
    INDEX
    Explanations

    code snippets and properties

    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
     tej
    -0.78
     Uz
    -0.73
    ffiche
    -0.72
    追踪
    -0.72
    hev
    -0.72
    ,,,,
    -0.71
    غيرة
    -0.71
    gebiet
    -0.69
    ேன்
    -0.69
    日で
    -0.68
    POSITIVE LOGITS
     Coven
    0.81
    
    0.79
     standardized
    0.78
     Standardized
    0.76
     Ensign
    0.76
    叫
    0.75
    的話
    0.75
    median
    0.73
    thereal
    0.73
     hebt
    0.73
    Activations Density 0.011%

    No Known Activations