© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59960
    Prev
    Next
    INDEX
    Explanations

    malnutrition and physical health

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

    descriptions of medical conditions related to malnutrition, weight loss, and eating disorders.

    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
     of
    -1.99
    ing
    -1.58
     it
    -1.30
     who
    -1.23
     this
    -1.20
     reaffirmed
    -1.18
     первая
    -1.17
     won
    -1.16
     first
    -1.15
    //
    -1.11
    POSITIVE LOGITS
     applau
    1.16
     nová
    1.14
    isChecked
    1.13
     BaseEntity
    1.13
    toCharArray
    1.12
    juste
    1.11
     میلیون
    1.10
     maniere
    1.10
     Conservative
    1.08
     الداخلية
    1.08
    Activations Density 0.037%

    No Known Activations