© 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. 75403
    Prev
    Next
    INDEX
    Explanations

    gelatinous sweets and baking ingredients

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

    The neuron is specialized to detect dessert‐related food terms and ingredients (e.g. jello/gelatin, brownies, cacao, pie crust).

    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
     strangle
    -1.80
    Partager
    -1.77
    Avantages
    -1.72
    Pratique
    -1.72
    Suivez
    -1.63
    when
    -1.59
    鏖
    -1.57
    Traduction
    -1.55
    Dès
    -1.55
    Lorsque
    -1.55
    POSITIVE LOGITS
     also
    1.31
     gleiche
    1.30
    and
    1.29
     et
    1.23
     volgens
    1.23
     緑
    1.20
     bütün
    1.18
    1
    1.18
    用的
    1.17
    GRESS
    1.16
    Activations Density 0.024%

    No Known Activations