© 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. 13797
    Prev
    Next
    INDEX
    Explanations

    programming data structures and code

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

    The neuron flags words that occur in quantitative contexts—i.e. terms tied to numbers, metrics, or measured values (ratios, percentages, points, prices, etc.).

    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
    。
    0.93
    ™.
    0.91
    ;
    0.90
    。《
    0.88
    。“
    0.86
    ។
    0.85
    ®.
    0.85
    ™,
    0.84
    ،
    0.83
    ,*
    0.82
    POSITIVE LOGITS
    ებულია
    0.75
     даних
    0.68
     actuellement
    0.68
     кстати
    0.65
     показателей
    0.65
    ულია
    0.65
    вами
    0.64
    десь
    0.64
     чем
    0.64
     actualmente
    0.63
    Activations Density 0.082%

    No Known Activations