© 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. 10-GEMMASCOPE-RES-131K
    7. 12127
    Prev
    Next
    INDEX
    Explanations

    state abbreviations N

    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_10/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
     now
    -2.84
     by
    -2.69
    y
    -2.55
    D
    -2.25
     not
    -2.25
     gets
    -2.23
     becomes
    -2.17
     Having
    -2.16
     from
    -2.14
     should
    -2.14
    POSITIVE LOGITS
    蕖
    2.50
    疴
    2.27
    熥
    2.20
    ︐
    2.17
    耵
    2.17
    
    2.13
    喾
    2.11
    泚
    2.09
    archiwizowane
    2.08
     "];
    2.05
    Activations Density 0.037%

    No Known Activations