© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45524
    Prev
    Next
    INDEX
    Explanations

    technical terms

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

    The neuron predominantly activates on content‐bearing nouns and specialized terms (e.g. developer, pages, styling, Bordeaux, whisky, programming).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     assurer
    -1.50
     
    -1.45
     carrés
    -1.42
     roues
    -1.38
     groupes
    -1.33
     créer
    -1.32
     TEXAS
    -1.31
    ?
    -1.30
     zui
    -1.30
    うーん
    -1.30
    POSITIVE LOGITS
     especially
    2.02
     during
    1.75
     with
    1.74
     at
    1.72
     through
    1.54
     becomes
    1.54
     özellikle
    1.52
     viejas
    1.51
     sees
    1.48
     Especially
    1.48
    Activations Density 0.413%

    No Known Activations