© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66256
    Prev
    Next
    INDEX
    Explanations

    numerical computation and algorithms

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

    The neuron fires on metadata tokens—URLs, version numbers, years, license labels, author names, and other header/citation elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    EMENTS
    -0.89
     jaws
    -0.76
     образу
    -0.75
     jurors
    -0.75
    Normalized
    -0.73
     correlates
    -0.71
    istanbul
    -0.69
     correlated
    -0.69
     encephal
    -0.68
     invertebrates
    -0.68
    POSITIVE LOGITS
     Numerical
    1.55
     numerical
    1.54
    Numerical
    1.48
     computational
    1.36
    numerical
    1.30
    Computational
    1.25
     Computational
    1.23
     SIAM
    1.20
     Computing
    1.19
     Numer
    1.14
    Activations Density 0.032%

    No Known Activations