© 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. 11243
    Prev
    Next
    INDEX
    Explanations

    company policies & procedures

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

    The neuron flags numeric tokens—integers or decimals (quantities, measurements, and standalone digits).

    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
    س
    0.82
     فرا
    0.72
    synt
    0.72
    こともある
    0.71
    ྜ
    0.70
     سرا
    0.69
    ים
    0.69
    abung
    0.68
    ット
    0.67
    ﺭ
    0.67
    POSITIVE LOGITS
    튿
    0.80
    uh
    0.72
    ៌
    0.72
    黍
    0.71
     anns
    0.70
    ум
    0.69
     успешно
    0.68
     назначения
    0.68
     Attach
    0.68
    が高い
    0.68
    Activations Density 0.000%

    No Known Activations