© 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. 14240
    Prev
    Next
    INDEX
    Explanations

    links, navigation, and code

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

    The neuron primarily activates on high-precision numeric values (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
     деятельности
    0.71
    トーク
    0.70
     изначально
    0.70
     достаточно
    0.67
    閆
    0.67
     informações
    0.66
     দেখিয়া
    0.66
     современной
    0.66
     бет
    0.66
     некоторые
    0.66
    POSITIVE LOGITS
     partir
    0.93
    ی
    0.89
     restitu
    0.84
    یب
    0.83
     scompar
    0.83
    یف
    0.82
    اریخ
    0.81
     attribu
    0.81
     pide
    0.80
     adipis
    0.80
    Activations Density 0.000%

    No Known Activations