© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4241
    Prev
    Next
    INDEX
    Explanations

    numbers and specific identifiers

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

    The neuron fires on words that begin sentences or clauses—especially capitalized discourse markers like “It,” “This,” “Besides,” or other tokens right after a period.

    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
     HEK
    0.88
     PARTICULAR
    0.83
    LET
    0.80
    ▥
    0.79
     Дело
    0.78
     Букмекерская
    0.77
     인간
    0.76
    Leia
    0.76
     Lactobacillus
    0.75
     NATURAL
    0.75
    POSITIVE LOGITS
    t
    0.98
    ductory
    0.79
    ir
    0.77
    ր
    0.75
    naments
    0.73
    お客様
    0.73
     festive
    0.71
    增速
    0.71
     seafront
    0.70
     swing
    0.70
    Activations Density 0.000%

    No Known Activations