© 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. 10431
    Prev
    Next
    INDEX
    Explanations

    chart builder, sql tables, file writer

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

    The neuron is keyed to section‐heading and metadata labels (e.g. category or field names) rather than normal running 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
     केयर
    0.57
     IntelliJ
    0.56
    asinya
    0.54
     $\%$
    0.54
    ிகள்
    0.54
     $-\
    0.54
     গ্রাম
    0.53
     Câu
    0.53
     analizar
    0.53
     ไง
    0.53
    POSITIVE LOGITS
    with
    0.65
    _
    0.58
    ༢
    0.54
    2
    0.54
    禁用
    0.53
    بع
    0.50
    宗
    0.50
    以外
    0.50
    Seed
    0.50
    Field
    0.48
    Activations Density 0.015%

    No Known Activations