© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90350
    Prev
    Next
    INDEX
    Explanations

    obesity and health contexts

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

    references to obesity and overweight conditions in medical or scientific 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
    ᯾
    -2.86
    嶮
    -2.72
    dzić
    -2.67
    紧接着
    -2.64
    垸
    -2.61
    鸸
    -2.61
    viembre
    -2.50
    ون
    -2.44
    ieR
    -2.36
    代わり
    -2.33
    POSITIVE LOGITS
    0
    4.81
    e
    4.03
    1
    3.66
    9
    3.48
    7
    3.41
    4
    3.38
    6
    3.19
    i
    3.11
    -
    3.11
    ↵
    3.09
    Activations Density 0.008%

    No Known Activations