© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27180
    Prev
    Next
    INDEX
    Explanations

    industry and its context

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

    The neuron lights up on terminology and phrasing typical of scientific or technical exposition—e.g. biological‐process words (cycles, regression, during, adult, life) and measurement‐oriented terms (mass, meters, parentheses) indicating a technical context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Choisissez
    -0.97
     EconPapers
    -0.96
     Trouvez
    -0.94
    šė
    -0.92
     appliquer
    -0.90
    namentales
    -0.88
     préférence
    -0.88
    
    -0.88
     Sélectionnez
    -0.87
     Prenez
    -0.87
    POSITIVE LOGITS
    propy
    0.85
     by
    0.85
     viele
    0.82
     comparable
    0.81
     through
    0.81
     namely
    0.80
     الطعام
    0.80
     very
    0.79
     tener
    0.75
    @@@
    0.75
    Activations Density 0.053%

    No Known Activations