© 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. 90339
    Prev
    Next
    INDEX
    Explanations

    corner or corners

    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
    ти
    -2.31
    li
    -1.75
    спомина
    -1.66
    ที่
    -1.63
    other
    -1.63
    
    -1.56
     of
    -1.52
    ли
    -1.52
    как
    -1.52
    зе
    -1.51
    POSITIVE LOGITS
    ();
    2.30
     ۱۱
    2.05
     ۱۳
    1.96
     ۱۷
    1.93
     ۶
    1.93
    ."
    1.93
     speziell
    1.89
     :).
    1.87
     ۳۰
    1.86
     ۱۶
    1.86
    Activations Density 0.007%

    No Known Activations