© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 540
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

    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
    It
    -2.33
     civili
    -2.33
    给我们
    -2.25
     It
    -2.23
    vantaged
    -2.22
    縐
    -2.22
     palio
    -2.20
    でしたが
    -2.20
     菇
    -2.20
    他还
    -2.19
    POSITIVE LOGITS
     gemens
    2.56
     одном
    2.50
    ية
    2.48
     anderen
    2.47
     sätt
    2.44
    那我
    2.42
     neues
    2.41
    ↵↵
    2.33
     hjälp
    2.31
     särsk
    2.31
    Activations Density 0.005%

    No Known Activations