© 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. 5913
    Prev
    Next
    INDEX
    Explanations

    technical or scientific context

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

    This neuron detects numeric tokens (digits or multi-digit numbers) in the text.

    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
     цьому
    0.64
     шанс
    0.64
     পাকিস্তানিদের
    0.60
     superstition
    0.59
     দোয়া
    0.59
     policymakers
    0.58
    ΤΑ
    0.57
    題
    0.57
     YEAR
    0.57
    দিন
    0.56
    POSITIVE LOGITS
     impeller
    0.75
    iaxial
    0.70
     protrusions
    0.69
     propeller
    0.68
     apertures
    0.68
     incision
    0.66
     waveguide
    0.64
    torque
    0.64
    incision
    0.64
     piezoelectric
    0.63
    Activations Density 0.026%

    No Known Activations