© 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. 10448
    Prev
    Next
    INDEX
    Explanations

    trustworthy, void, driver, engine

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

    The neuron fires on any kind of explicit enumeration token—digits or spelled-out numbers (and the little “of the” scaffolding around them) that mark list‐ or count‐style references.

    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
     simplices
    0.93
     alcoved
    0.89
     polytopes
    0.88
    ーブ
    0.84
    ointees
    0.84
    tır
    0.84
    coelastic
    0.83
    u
    0.83
    יות
    0.82
     emptying
    0.82
    POSITIVE LOGITS
    ode
    0.84
    кий
    0.81
    ပါသည်။
    0.75
    ë
    0.69
    ırmak
    0.68
    );*/
    0.66
    ote
    0.65
     rider
    0.65
     favor
    0.64
     través
    0.64
    Activations Density 0.003%

    No Known Activations