© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103607
    Prev
    Next
    INDEX
    Explanations

    signs and symptoms

    np_acts-logits-general · gemini-2.5-flash-lite

    references to medical or diagnostic signs in healthcare and clinical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    *
    -2.48
     
    -2.25
     crammed
    -2.23
     While
    -2.19
     並
    -2.16
     entice
    -2.06
    不得不说
    -2.05
     annoyed
    -1.96
    一个是
    -1.95
    鶲
    -1.95
    POSITIVE LOGITS
    a
    2.78
    u
    2.69
    e
    2.63
     signs
    2.52
     protože
    2.34
    僦
    2.34
    ar
    2.31
    蕷
    2.30
    y
    2.28
    s
    2.25
    Activations Density 0.005%

    No Known Activations