© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1780
    Prev
    Next
    INDEX
    Explanations

    baking and cooking recipes

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

    The neuron fires strongly on content-bearing words (nouns, verbs, adjectives, and other “real” words) while ignoring common function words and punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hab
    0.64
     elucid
    0.64
     валю
    0.63
    🛡
    0.63
    BLACKLIST
    0.62
     StatusCode
    0.61
     Versicherung
    0.61
     Standort
    0.61
     tutela
    0.60
    🤬
    0.60
    POSITIVE LOGITS
     baking
    1.70
     recipes
    1.66
     bake
    1.65
     casserole
    1.63
     muffins
    1.62
     freezer
    1.59
     leftovers
    1.57
     appetizers
    1.57
     recipe
    1.56
     cupcakes
    1.55
    Activations Density 1.947%

    No Known Activations