© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103382
    Prev
    Next
    INDEX
    Explanations

    include directives and file names

    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
     Theo
    -0.75
     wybran
    -0.73
    Mikro
    -0.73
    Rejection
    -0.73
    otype
    -0.72
    誇
    -0.72
     И
    -0.70
     helpless
    -0.69
     картин
    -0.69
     Through
    -0.67
    POSITIVE LOGITS
     本
    0.98
    ánló
    0.96
     szám
    0.93
    hems
    0.91
    tsa
    0.90
    ⚃
    0.87
     almonds
    0.85
    }}^{
    0.85
    ഫ
    0.85
     pág
    0.85
    Activations Density 0.006%

    No Known Activations