© 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. 4749
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code delimiters

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

    This neuron responds to numeric tokens and other tokens that appear in numbers or web/URL-like contexts.

    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
    که
    0.72
    وه
    0.68
    u
    0.68
    វា
    0.66
     Absence
    0.65
    مر
    0.64
    ساس
    0.64
    MIX
    0.64
    ھ
    0.64
    Card
    0.63
    POSITIVE LOGITS
     prerog
    0.87
     бушлай
    0.81
    gcj
    0.78
    avorites
    0.76
     truly
    0.75
    liness
    0.75
     annuities
    0.73
     бесплатно
    0.72
     치료
    0.71
    materials
    0.71
    Activations Density 0.001%

    No Known Activations