© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4786
    Prev
    Next
    INDEX
    Explanations

    minimum length

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

    The neuron activates on technical or methodological terms describing formal processes, algorithms, analyses, or procedural steps.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aptly
    0.57
    a
    0.57
     testament
    0.55
    同年
    0.55
     teas
    0.54
    धिकार
    0.54
     emeritus
    0.54
     다르
    0.54
    샵
    0.53
     customs
    0.53
    POSITIVE LOGITS
    argmax
    0.64
    imax
    0.64
     величина
    0.64
    argmin
    0.64
    RMSE
    0.63
     UpdateWindow
    0.63
     optimizing
    0.62
    Optimization
    0.62
    Metrics
    0.61
     статисти
    0.61
    Activations Density 0.153%

    No Known Activations