© 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. 59320
    Prev
    Next
    INDEX
    Explanations

    additive effects or manufacturing

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

    The neuron is strongly activated by the word “additive.”

    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
    ’
    -2.08
    不该
    -2.08
    ໊
    -2.06
    pinephrine
    -2.00
    褔
    -1.98
    cterms
    -1.97
     Gå
    -1.95
     ܙ
    -1.95
     warmen
    -1.93
    .}(
    -1.92
    POSITIVE LOGITS
     και
    2.63
     и
    2.38
     và
    2.30
     și
    2.22
    概述
    2.17
    你
    2.17
    ра
    2.06
     และ
    2.06
    并且
    2.05
     sabias
    2.05
    Activations Density 0.003%

    No Known Activations