© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13921
    Prev
    Next
    INDEX
    Explanations

    seasoned / seasoning

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

    The neuron activates on words naming seasonings, spices, or flavoring agents.

    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
    c
    -2.69
    (
    -2.47
    [
    -2.34
    t
    -2.22
     three
    -2.14
     plethora
    -2.03
     frightening
    -2.03
    }\
    -1.98
    s
    -1.98
     pervasive
    -1.94
    POSITIVE LOGITS
    に行く
    1.84
     ſont
    1.73
    tauchen
    1.72
     刺繍
    1.69
     レザー
    1.63
     profond
    1.63
    縻
    1.62
     الرخصة
    1.60
     titans
    1.58
     フレア
    1.58
    Activations Density 0.001%

    No Known Activations