© 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. 41381
    Prev
    Next
    INDEX
    Explanations

    corrected, miscellaneous

    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
    籥
    -2.77
    琑
    -2.45
    blurRadius
    -2.36
    ꜆
    -2.33
    忍受
    -2.33
     he
    -2.31
     collaborate
    -2.25
    猻
    -2.23
    StoryboardSegue
    -2.23
     capitalize
    -2.23
    POSITIVE LOGITS
    ↵
    3.33
    ’
    3.14
    ዣ
    2.95
    ated
    2.48
    ープン
    2.42
    觏
    2.42
    额外
    2.36
    ']
    2.34
    采用了
    2.31
    the
    2.28
    Activations Density 0.006%

    No Known Activations