© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13272
    Prev
    Next
    INDEX
    Explanations

    intelligence ( definitions

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

    The neuron selectively fires on multi‐word technical or specialized jargon phrases (e.g. “advanced persistent threat,” “intrusion detection system,” “return on investment,” “analytical technology”).

    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
    الية
    0.71
    /
    0.71
    u
    0.70
    و
    0.70
    럿
    0.68
     dll
    0.68
    /'
    0.68
    ας
    0.67
    ../
    0.66
    ฯ
    0.64
    POSITIVE LOGITS
     $(\
    0.98
     (
    0.95
    简称
    0.90
    $(\
    0.82
     यानी
    0.77
    」(
    0.76
    <h6>
    0.74
    çalves
    0.74
     પ્રકાર
    0.73
    ূল্যে
    0.72
    Activations Density 1.196%

    No Known Activations