© 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. 7374
    Prev
    Next
    INDEX
    Explanations

    react code

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

    The neuron fires chiefly on digit‐containing tokens (i.e. numbers and numeric substrings).

    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
    كتر
    0.71
     כך
    0.71
    bild
    0.70
    tk
    0.69
    mj
    0.67
    werke
    0.66
     Dijkstra
    0.65
    毯
    0.64
    не
    0.64
    respon
    0.64
    POSITIVE LOGITS
    品种
    0.79
     situate
    0.79
     setan
    0.78
    航班
    0.78
     cóm
    0.73
    常规
    0.73
     donnent
    0.72
     agrí
    0.71
     світу
    0.71
    azor
    0.71
    Activations Density 0.003%

    No Known Activations