© 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. 13990
    Prev
    Next
    INDEX
    Explanations

    citations and titles

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

    The neuron activates on floating‐point numerical values (decimal numbers).

    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
    appartement
    0.53
    雬
    0.50
    fonction
    0.49
    yní
    0.49
    鿉
    0.48
    agle
    0.48
    même
    0.48
    quement
    0.48
    ॉग
    0.47
    antwoord
    0.47
    POSITIVE LOGITS
     Neuro
    0.60
     neuro
    0.59
     }}$,
    0.57
    出版
    0.57
    Neuro
    0.57
     Obsidian
    0.57
     indiscrimin
    0.54
     かわいい
    0.54
     psyk
    0.54
    융
    0.53
    Activations Density 0.002%

    No Known Activations