© 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. 14771
    Prev
    Next
    INDEX
    Explanations

    Satan, smtp, datatable, Sustainable, Eleven

    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
    凊
    -2.86
    苙
    -2.63
    霂
    -2.58
     übri
    -2.48
    ៦
    -2.48
    
    -2.44
    呓
    -2.42
    
    -2.42
     =
    -2.39
     gesamte
    -2.36
    POSITIVE LOGITS
    牁
    3.88
    蟶
    2.94
    硨
    2.83
    </b>
    2.70
     nouveau
    2.67
    ༵
    2.56
    蛩
    2.52
    ፱
    2.48
     Desember
    2.47
     "}
    2.45
    Activations Density 0.001%

    No Known Activations