© 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. 8889
    Prev
    Next
    INDEX
    Explanations

    file system paths and commands

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

    The neuron primarily responds to numeric tokens—especially decimal numbers or other numeric measurements.

    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
    ü
    0.82
    mente
    0.77
    trying
    0.75
    λή
    0.74
    dis
    0.74
     constitución
    0.74
    उन्होंने
    0.73
    den
    0.73
    ли
    0.72
    ten
    0.72
    POSITIVE LOGITS
     связанные
    0.73
     اما
    0.73
    ≿
    0.73
    сне
    0.73
     touted
    0.72
     coronary
    0.71
     ESTIM
    0.71
     estimated
    0.70
    ERIAL
    0.70
     eroded
    0.70
    Activations Density 0.000%

    No Known Activations