© 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. 7956
    Prev
    Next
    INDEX
    Explanations

    hair length

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

    The neuron is specialized to detect numeric tokens (especially multi‐digit or decimal 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
    een
    0.78
     וח
    0.77
     Emeritus
    0.75
    ^{'
    0.75
     Prado
    0.73
    ндә
    0.73
    ﻭ
    0.71
     etn
    0.71
    з
    0.70
    NN
    0.70
    POSITIVE LOGITS
    ى
    0.82
    duğu
    0.77
     afield
    0.74
    র্ডার
    0.74
    iają
    0.73
    atifs
    0.73
     faç
    0.72
    ジュアル
    0.72
     cliquez
    0.72
     DECIMAL
    0.72
    Activations Density 0.000%

    No Known Activations