© 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. 10765
    Prev
    Next
    INDEX
    Explanations

    creation, processing, assignment

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

    The neuron detects content-heading or topic words (often nouns or gerunds) that label major sections in formal/technical documents.

    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
    ordable
    0.64
    ྃ
    0.63
    OrCallback
    0.60
    ல்லாம்
    0.59
    での
    0.57
    বিশিষ্ট
    0.56
     Premiership
    0.54
     பொருளாதார
    0.54
     প্রয
    0.53
    ၈
    0.53
    POSITIVE LOGITS
     avanc
    0.68
     indes
    0.67
     ina
    0.63
     am
    0.62
    veri
    0.61
     stata
    0.60
    ులు
    0.60
     hilo
    0.60
     incompar
    0.59
    anek
    0.58
    Activations Density 0.012%

    No Known Activations