© 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. 13975
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming terms

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

    The neuron chiefly detects numeric tokens formatted as floating‐point or multi‐digit 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
     lattices
    0.84
    ंटो
    0.79
     maternelle
    0.79
    ຯ
    0.76
     corpus
    0.76
    东西
    0.75
     monolayers
    0.75
     реали
    0.75
     wrap
    0.74
     moneda
    0.72
    POSITIVE LOGITS
    i
    1.02
    0.95
     P
    0.83
    or
    0.82
    in
    0.81
    Z
    0.81
    Х
    0.80
     H
    0.80
     Canc
    0.79
    7
    0.79
    Activations Density 0.000%

    No Known Activations