© 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. 10945
    Prev
    Next
    INDEX
    Explanations

    want to

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

    The neuron strongly activates on dense, formal mathematical statements or technical academic writing (e.g. theorem‐ or proof‐style passages).

    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
    oprene
    0.66
    Ų
    0.66
     বায়ু
    0.64
    RMSE
    0.62
    SARS
    0.60
     ऑपरेटिंग
    0.60
    rilor
    0.60
    ulnerable
    0.60
    MUST
    0.60
     ننوت
    0.60
    POSITIVE LOGITS
     semigroup
    0.79
     Drinfeld
    0.74
     algebras
    0.72
     classes
    0.70
    𝚐
    0.70
     grants
    0.70
     obstructions
    0.69
     morphisms
    0.69
     extensions
    0.68
     theorems
    0.68
    Activations Density 0.002%

    No Known Activations