© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11882
    Prev
    Next
    INDEX
    Explanations

    math and code symbols

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

    The neuron strongly activates on numeric expressions (e.g. numbers, years, ordinals).

    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
     پری
    0.82
    。
    0.81
    此同时
    0.77
     auk
    0.77
     اﻻ
    0.77
    ルド
    0.76
     Gub
    0.76
    ।
    0.76
     rischi
    0.75
     inferiores
    0.75
    POSITIVE LOGITS
    大家好
    0.82
     शकत
    0.81
    mun
    0.80
    по
    0.77
    कल्प
    0.76
    uz
    0.73
    ስ
    0.73
    alignat
    0.73
    নাথ
    0.72
    Ocean
    0.72
    Activations Density 0.000%

    No Known Activations