© 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. 105782
    Prev
    Next
    INDEX
    Explanations

    egg white and meringue

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

    food ingredients with emphasis on egg whites and protein sources.

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

    The neuron activates on mentions of egg‐white or egg‐white–derived substances (including recipes and proteins like ovalbumin).

    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
     is
    -1.66
    ing
    -1.55
     from
    -1.48
     such
    -1.45
    -
    -1.41
     of
    -1.35
    u
    -1.34
    或者
    -1.30
     siehe
    -1.29
     says
    -1.26
    POSITIVE LOGITS
     メニュー
    1.72
    ம
    1.45
     decorated
    1.41
    பெ
    1.35
    鱺
    1.34
     eren
    1.34
    🖋
    1.32
     portátil
    1.31
     Vitória
    1.30
    婓
    1.30
    Activations Density 0.013%

    No Known Activations