© 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. 11929
    Prev
    Next
    INDEX
    Explanations

    half of, century ago

    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
     jsou
    -1.86
    鵟
    -1.84
    艽
    -1.82
    癣
    -1.79
     Архиви
    -1.76
    kwür
    -1.74
     ก็
    -1.73
    垌
    -1.72
    ismer
    -1.71
     retratos
    -1.66
    POSITIVE LOGITS
    ↵↵
    2.42
     erstes
    2.22
     —
    2.22
    
    2.06
    e
    1.98
    9
    1.95
     daga
    1.92
    0
    1.91
     are
    1.91
    in
    1.91
    Activations Density 0.083%

    No Known Activations