© 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. 104421
    Prev
    Next
    INDEX
    Explanations

    roman letters

    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
    )$
    -2.14
    </sup>
    -1.98
    J
    -1.95
    C
    -1.85
    X
    -1.74
    V
    -1.73
    f
    -1.71
    P
    -1.71
    t
    -1.69
    N
    -1.69
    POSITIVE LOGITS
    鹮
    2.02
    ,  
    1.93
    鸶
    1.76
    omores
    1.73
     การ์ตูน
    1.72
    彇
    1.72
    gucig
    1.70
     extraordinaire
    1.67
    鹟
    1.63
    锈
    1.62
    Activations Density 0.125%

    No Known Activations