© 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. 14400
    Prev
    Next
    INDEX
    Explanations

    specifically, this climate bold investing while

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

    The neuron activates on tokens containing digits (numbers, years, or numeric sequences).

    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
    㓡
    0.65
    द्योगिकी
    0.60
    㫻
    0.59
    fuss
    0.59
    ナソニック
    0.58
    镟
    0.58
     Investigación
    0.58
    hehi
    0.57
    㭂
    0.57
    ironolactone
    0.56
    POSITIVE LOGITS
     tetapi
    0.55
     but
    0.55
    Components
    0.53
    ที่
    0.50
    That
    0.50
     berdiri
    0.50
    でしたが
    0.50
    에서
    0.50
    ที่มี
    0.49
    of
    0.49
    Activations Density 0.071%

    No Known Activations