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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109912
    Prev
    Next
    INDEX
    Explanations

    children's hospitals and charities

    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
    叨
    -0.77
    órum
    -0.76
     uVar
    -0.74
     Kontexten
    -0.73
     m
    -0.73
     Black
    -0.73
    /
    -0.73
    老年
    -0.72
    +
    -0.72
    code
    -0.71
    POSITIVE LOGITS
     children
    1.63
     pediatric
    1.53
    Children
    1.37
    ediatric
    1.35
     families
    1.32
     Pediatric
    1.29
     Children
    1.23
     Ronald
    1.21
     CHILDREN
    1.19
    Ronald
    1.19
    Activations Density 0.036%

    No Known Activations