© 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. 8184
    Prev
    Next
    INDEX
    Explanations

    generally or significantly

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

    The neuron is specialized for spotting numeric tokens that include decimal points (i.e. floating‐point 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
    持續
    0.82
    勞
    0.73
     venant
    0.72
    彎
    0.70
     owners
    0.70
    賴
    0.70
    一句
    0.69
    數據
    0.69
    INATION
    0.69
    分數
    0.69
    POSITIVE LOGITS
    in
    0.83
     Acta
    0.83
    ⅾ
    0.82
     дает
    0.80
    ԁ
    0.77
     stipulates
    0.77
     Optionally
    0.76
    ніка
    0.76
     만큼
    0.74
    यों
    0.74
    Activations Density 0.000%

    No Known Activations