© 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. 297
    Prev
    Next
    INDEX
    Explanations

    Guth/Gut/Gutt names and utter/utta

    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
    
    -3.17
    킁
    -2.72
    猻
    -2.67
    艄
    -2.41
    呶
    -2.34
    ㍑
    -2.34
    
    -2.34
     doigt
    -2.28
    屺
    -2.27
    obviously
    -2.23
    POSITIVE LOGITS
    ↵
    3.06
     When
    2.69
    外的
    2.59
     '
    2.56
     prácticamente
    2.39
     Other
    2.30
     That
    2.14
    遢
    2.13
    </h1>
    2.08
    ).
    2.08
    Activations Density 0.001%

    No Known Activations