© 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. 22-GEMMASCOPE-RES-131K
    7. 13178
    Prev
    Next
    INDEX
    Explanations

    software filenames and code

    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_22/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
     ۱۱
    -0.97
    Кон
    -0.96
     PARSER
    -0.94
    alignItems
    -0.92
     consulté
    -0.92
     марке
    -0.91
     incomplète
    -0.90
    着脸
    -0.90
     negativa
    -0.90
     ziren
    -0.90
    POSITIVE LOGITS
    ’
    1.00
    cough
    0.95
     entweder
    0.91
     centric
    0.90
    both
    0.90
     caucasian
    0.90
     heridos
    0.86
     premed
    0.85
    んでも
    0.85
    大丈夫です
    0.85
    Activations Density 0.000%

    No Known Activations