© 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. 14116
    Prev
    Next
    INDEX
    Explanations

    introductions and lists

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

    This neuron fires on sentence- and clause-boundary markers—e.g. punctuation like commas and periods and the first word of a new sentence (especially transition words like “However,” “In,” “He,” 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
     نیز
    0.68
    
    0.66
     handicrafts
    0.65
     зарегистри
    0.64
     verwendeten
    0.62
     THEIR
    0.62
     perusahaan
    0.61
     آنان
    0.60
     ഉത്സ
    0.59
     企业
    0.58
    POSITIVE LOGITS
    de
    0.63
     matchup
    0.62
    /
    0.62
    пит
    0.61
     offseason
    0.59
    ante
    0.59
     gotta
    0.58
     underrated
    0.57
    現状
    0.57
    cektir
    0.56
    Activations Density 0.232%

    No Known Activations