© 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. 123825
    Prev
    Next
    INDEX
    Explanations

    meeting daily nutritional requirements

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

    nutrition-related information about daily dietary intake requirements and recommendations.

    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
     to
    -1.13
     beig
    -1.10
     accepter
    -1.05
     this
    -1.05
     осен
    -1.04
     precis
    -1.03
     Lerner
    -1.02
     CERTAIN
    -1.02
     sui
    -1.01
    结语
    -1.01
    POSITIVE LOGITS
     YEAR
    1.27
     Entste
    1.26
     róż
    1.23
    карта
    1.22
     year
    1.20
    cians
    1.20
     lèvres
    1.20
     sought
    1.20
     week
    1.19
    </h4>
    1.16
    Activations Density 0.084%

    No Known Activations