© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8278
    Prev
    Next
    INDEX
    Explanations

    arts and artist

    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
    \
    -1.98
    来自于
    -1.95
    近くに
    -1.95
    能在
    -1.87
     brasileira
    -1.85
    ଝ
    -1.81
     AMERICA
    -1.74
    
    -1.73
    ?
    -1.73
     моей
    -1.73
    POSITIVE LOGITS
     probabilmente
    2.13
     Zeitraum
    2.08
    ?”
    2.06
     становятся
    2.03
     decadent
    2.03
     wichtigen
    2.02
     will
    2.02
     somber
    1.98
     persino
    1.97
     办
    1.95
    Activations Density 0.003%

    No Known Activations