© 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. 5912
    Prev
    Next
    INDEX
    Explanations

    sequential token relationships

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

    The neuron consistently lights up on words appearing in technical or factual “spec sheet” style contexts—e.g. product specs, measurements, schedules, or enumerated details.

    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
    0.87
    il
    0.84
    การ
    0.80
     Internet
    0.77
    تر
    0.74
    ت
    0.73
    EN
    0.70
     personnel
    0.70
     .
    0.69
     officer
    0.69
    POSITIVE LOGITS
    ၃
    0.88
    ൦
    0.86
    分からない
    0.80
    ।’
    0.76
     целей
    0.76
     등의
    0.76
    觕
    0.74
    tencent
    0.73
    ponds
    0.73
    ᱐
    0.73
    Activations Density 0.000%

    No Known Activations