© 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. 81497
    Prev
    Next
    INDEX
    Explanations

    win-loss record

    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
    listers
    -0.88
     ayudarte
    -0.85
    択
    -0.76
    Å
    -0.75
     favoritos
    -0.74
     LOW
    -0.73
    [`
    -0.73
    LOW
    -0.73
     ay
    -0.73
     aload
    -0.72
    POSITIVE LOGITS
     record
    4.97
    record
    4.00
     records
    3.72
    Record
    3.61
     Record
    3.53
    RECORD
    3.27
     RECORD
    3.03
    records
    2.95
    Records
    2.67
     Records
    2.66
    Activations Density 0.058%

    No Known Activations