© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3275
    Prev
    Next
    INDEX
    Explanations

    before Transformers

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

    The neuron is detecting large numeric tokens (especially floating‐point numbers).

    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
    ："
    0.60
     mononuclear
    0.60
     不是
    0.60
    ：
    0.59
     Physiological
    0.57
    ла
    0.57
     의한
    0.57
    孔
    0.57
    getActiveSheet
    0.56
    Panoramic
    0.56
    POSITIVE LOGITS
     आईआई
    0.57
    salary
    0.57
     करियर
    0.57
     그거
    0.55
     obsession
    0.54
     staffers
    0.54
     kojima
    0.53
     службу
    0.52
     buyout
    0.52
    Citi
    0.52
    Activations Density 0.001%

    No Known Activations