© 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. 10-GEMMASCOPE-RES-131K
    4. 61245
    Prev
    Next
    INDEX
    Explanations

    describing experimental conditions

    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
     内衣
    -1.78
    鼍
    -1.73
    🫴
    -1.71
     estadounid
    -1.67
     theolog
    -1.66
    棡
    -1.63
    糁
    -1.63
    various
    -1.61
     特写
    -1.61
    ➕
    -1.60
    POSITIVE LOGITS
    ↵↵
    1.77
    in
    1.73
     ie
    1.63
    .
    1.54
    過的
    1.40
     conditions
    1.38
     omit
    1.31
    どうなる
    1.31
     twórc
    1.30
    感じで
    1.28
    Activations Density 0.055%

    No Known Activations