© 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. 12421
    Prev
    Next
    INDEX
    Explanations

    code imports

    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
    o
    -1.93
     empfind
    -1.91
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.75
    ,
    -1.75
    .
    -1.69
    徐々に
    -1.66
     agonizing
    -1.58
     véhic
    -1.57
    --
    -1.56
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.54
    POSITIVE LOGITS
     we
    2.06
     have
    2.02
     Internasional
    1.88
     camara
    1.84
     that
    1.84
     futebol
    1.83
    \}$.
    1.80
     truk
    1.79
     Commissione
    1.76
     trattato
    1.75
    Activations Density 0.012%

    No Known Activations