© 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. 13678
    Prev
    Next
    INDEX
    Explanations

    converts or breaks down phrases

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

    The neuron strongly activates on numeric quantities (years, counts, measures) and surrounding numerical expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words or tokens that appear just before punctuation or transition points in promotional or procedural web content.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    clause-leading words that introduce or emphasize main statements in expository or promotional sentences.

    oai_token-act-pair · gpt-5Triggered 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
    ytically
    0.82
     ሂ
    0.73
     creen
    0.72
     adduct
    0.70
     comet
    0.70
    ic
    0.69
     தமது
    0.69
     lp
    0.67
     decedent
    0.67
    ரி
    0.66
    POSITIVE LOGITS
    Есть
    1.06
    Чтобы
    0.99
    Как
    0.99
    С
    0.98
    Все
    0.97
    Los
    0.96
    Вы
    0.96
    Bueno
    0.95
    По
    0.95
    Kako
    0.94
    Activations Density 0.000%

    No Known Activations