© 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. 100023
    Prev
    Next
    INDEX
    Explanations

    trucks and trailers

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

    This neuron responds to mentions of large road vehicles (e.g. trucks, lorries, buses, trailers).

    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
    躂
    -1.50
    beratung
    -1.43
    Trayectoria
    -1.38
    REMARKS
    -1.33
    𞤢
    -1.31
    大豆
    -1.30
     flesta
    -1.28
    Hintergrund
    -1.28
    Biografía
    -1.27
     Wortes
    -1.27
    POSITIVE LOGITS
    rigos
    1.34
     is
    1.31
     trucks
    1.30
    iao
    1.29
     jette
    1.27
    そこから
    1.23
    k
    1.23
    romic
    1.22
     Umum
    1.22
     cercano
    1.22
    Activations Density 0.037%

    No Known Activations