© 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. 10707
    Prev
    Next
    INDEX
    Explanations

    commute or complement

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

    This neuron primarily detects decimal-form numbers (floating-point numerals) such as those in page or volume citations.

    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
    Si
    0.92
    La
    0.86
    O
    0.80
    С
    0.79
    、
    0.76
    ksi
    0.75
    re
    0.75
    J
    0.75
    Њ
    0.75
    B
    0.74
    POSITIVE LOGITS
     отказыва
    0.85
     shaved
    0.81
     austenitic
    0.81
     buoyant
    0.80
     impediments
    0.79
     lunatic
    0.79
     अमाउंट
    0.78
     бухгал
    0.77
     polymorphic
    0.77
     uttered
    0.77
    Activations Density 0.000%

    No Known Activations