© 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. 22-GEMMASCOPE-RES-131K
    7. 65674
    Prev
    Next
    INDEX
    Explanations

    medical, biological, and human activities

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

    medical and scientific terms related to diseases, treatments, and substances in healthcare 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_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
    6
    -1.38
    7
    -1.27
     when
    -1.27
     künftig
    -1.21
    8
    -1.21
     after
    -1.20
    v
    -1.16
    f
    -1.16
    3
    -1.16
    b
    -1.15
    POSITIVE LOGITS
     such
    1.68
     choisi
    1.33
    xxi
    1.32
     oublier
    1.27
     craindre
    1.22
    specially
    1.20
    
    1.19
    certain
    1.16
     including
    1.15
     tertentu
    1.14
    Activations Density 0.157%

    No Known Activations