© 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. 12711
    Prev
    Next
    INDEX
    Explanations

    skin tone

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

    This neuron detects numeric tokens (numbers, decimals, IDs, measurements, etc.) in the 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
    полне
    0.80
    య
    0.76
    чным
    0.72
    情形
    0.70
    աստ
    0.69
    を得
    0.68
    เข้า
    0.66
     Еще
    0.66
    𝗨
    0.66
     chronically
    0.65
    POSITIVE LOGITS
     paragraphe
    0.93
     싶은
    0.89
     passato
    0.89
     съм
    0.88
    tedir
    0.86
    ee
    0.84
     관련된
    0.82
    에
    0.81
    ુ
    0.81
    efois
    0.81
    Activations Density 0.000%

    No Known Activations