© 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. 22-GEMMASCOPE-RES-131K
    4. 11013
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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_22/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
     其他
    -0.86
     aucune
    -0.79
     occafion
    -0.78
    )}_
    -0.77
    gren
    -0.76
    источник
    -0.76
     Interpreter
    -0.75
    味的
    -0.75
     svolge
    -0.75
     incontr
    -0.75
    POSITIVE LOGITS
    ":
    
    1.16
     safe
    1.05
    Saf
    1.02
     housework
    1.01
    "):
    
    0.91
     safely
    0.91
     what
    0.91
     equivalents
    0.91
     without
    0.91
     Saf
    0.91
    Activations Density 0.087%

    No Known Activations