© 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. 19573
    Prev
    Next
    INDEX
    Explanations

    italic, strict equal, maintain, Q, n, Andorra

    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
     dlouho
    -1.98
     dużo
    -1.79
     a
    -1.72
     longterm
    -1.67
     erläut
    -1.63
     znacznie
    -1.63
     obecnie
    -1.59
     slew
    -1.55
    ̈r
    -1.54
     imprescindible
    -1.53
    POSITIVE LOGITS
    ῞
    1.92
    豨
    1.90
     picante
    1.84
    鳝
    1.84
    轵
    1.82
    3
    1.80
    牐
    1.78
     cirka
    1.78
    禤
    1.73
     rambut
    1.72
    Activations Density 0.000%

    No Known Activations