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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84076
    Prev
    Next
    INDEX
    Explanations

    strange results, output, things

    np_acts-logits-general · gemini-2.5-flash-lite

    the exact word “strange” (in any context or casing)

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    
    -2.88
    廛
    -2.78
    卺
    -2.69
    蟥
    -2.66
    
    -2.64
    
    -2.64
    푆
    -2.63
    癭
    -2.58
    皤
    -2.58
    喁
    -2.58
    POSITIVE LOGITS
     —
    3.14
    ).
    2.98
    .
    2.94
    ?
    2.92
     That
    2.88
     Interestingly
    2.80
    而又
    2.77
     Surprisingly
    2.77
    ),
    2.70
     Ironically
    2.67
    Activations Density 0.003%

    No Known Activations