© 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. 7741
    Prev
    Next
    INDEX
    Explanations

    with or without certain conditions

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

    The neuron selectively fires on uppercase alphanumeric tokens (product or section identifiers, model names, and codes).

    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
    夂
    0.82
    writer
    0.77
    歌手
    0.76
    たくさん
    0.75
    返回值
    0.71
     Recuper
    0.71
    体会
    0.71
     Tử
    0.70
    শিশ
    0.68
    㱛
    0.68
    POSITIVE LOGITS
     zonder
    1.01
     tanpa
    0.95
     ohne
    0.91
     without
    0.91
     unrestricted
    0.89
     klassischen
    0.87
     normalen
    0.87
     freien
    0.85
     без
    0.80
     بدون
    0.80
    Activations Density 3.200%

    No Known Activations