Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8738
    Prev
    Next
    INDEX
    Explanations

    minds/lives/hands/eyes of

    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_34/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
     føl
    -1.02
    práv
    -0.98
     privind
    -0.92
     Wirkungen
    -0.91
     nemlig
    -0.88
     spør
    -0.88
     réparation
    -0.86
     quoc
    -0.86
     hjæl
    -0.86
     utilidad
    -0.86
    POSITIVE LOGITS
     of
    3.77
    ของ
    1.59
     của
    1.39
     degli
    1.37
     των
    1.34
     ofthe
    1.23
     dels
    1.02
     του
    1.02
    ÓW
    0.99
    ของคุณ
    0.97
    Activations Density 0.044%

    No Known Activations