© 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. 20492
    Prev
    Next
    INDEX
    Explanations

    types of meat and fish

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

    words related to types of meat and seafood in culinary contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on words naming animal-based foods—especially meats and game (e.g., turkey, lamb, partridge).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     empresa
    -1.30
     reager
    -1.27
     věci
    -1.27
    Karakteristik
    -1.27
    тування
    -1.24
    ейс
    -1.21
    攆
    -1.20
     แต่
    -1.20
     zijn
    -1.20
     artikel
    -1.19
    POSITIVE LOGITS
     when
    1.61
     we
    1.49
     while
    1.48
    Like
    1.42
     by
    1.41
    `)
    1.41
    Only
    1.38
    When
    1.37
     знает
    1.36
    So
    1.34
    Activations Density 0.026%

    No Known Activations