© 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. 15703
    Prev
    Next
    INDEX
    Explanations

    height measurements (feet and inches)

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

    The neuron fires on the first substantive word of a new sentence or block, effectively detecting sentence‐ or paragraph‐initial tokens.

    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
    اح
    0.86
    اد
    0.83
    ك
    0.78
    وو
    0.77
    ي
    0.76
    ବ
    0.75
    يك
    0.73
    স
    0.73
    ಬು
    0.72
    ходом
    0.70
    POSITIVE LOGITS
    taj
    0.79
    ↵
    0.78
     سوری
    0.77
     Busch
    0.75
     Algonquin
    0.74
    </
    0.74
    ężczy
    0.73
     элемент
    0.72
    derive
    0.71
    PSO
    0.71
    Activations Density 0.000%

    No Known Activations