© 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. 10269
    Prev
    Next
    INDEX
    Explanations

    numbers and list items

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

    The neuron fires on questions that request quantitative or numeric information (e.g. “How much…?”, “How long…?”, “What dosage…?”).

    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
     neutrophil
    0.75
    indazole
    0.68
    thorace
    0.66
     uterine
    0.66
     ẞ
    0.64
    lbrakk
    0.62
     ширина
    0.62
     manifi
    0.61
     epithelial
    0.59
    িকপ্ট
    0.59
    POSITIVE LOGITS
    :
    0.73
    ↵
    0.71
    People
    0.69
    Everyone
    0.67
    Corporate
    0.67
    ↵↵
    0.66
    Investors
    0.65
    Someone
    0.64
    Andrew
    0.64
     Auditors
    0.64
    Activations Density 0.117%

    No Known Activations