© 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. 15790
    Prev
    Next
    INDEX
    Explanations

    code-like punctuation or symbols

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

    The neuron is a strong detector for numeric tokens or numbers (dates, measurements, counts, codes, etc.) 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
     Temmuz
    0.87
    um
    0.84
    ور
    0.79
    :
    0.78
    Thursday
    0.75
    u
    0.75
    oflav
    0.73
    igin
    0.73
    November
    0.72
     implica
    0.72
    POSITIVE LOGITS
    ﻴ
    0.91
     Вообще
    0.88
    ﻨ
    0.85
     monto
    0.84
     Некоторые
    0.80
     cantidad
    0.80
     reorganization
    0.78
     են
    0.78
     americanos
    0.75
    ﻔ
    0.75
    Activations Density 0.000%

    No Known Activations