© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11176
    Prev
    Next
    INDEX
    Explanations

    HTML tags or code-like elements

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

    The neuron strongly activates on numeric tokens (especially floating‐point or other number values).

    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
     ござい
    0.85
     Mentre
    0.80
     Phật
    0.79
     今
    0.78
    ج
    0.77
     Physiological
    0.77
     March
    0.75
     marzo
    0.75
     Questi
    0.75
    場合の
    0.75
    POSITIVE LOGITS
    UNIC
    0.95
    ्स
    0.84
    словно
    0.81
    unic
    0.79
    Unis
    0.73
    DUP
    0.73
    ukaan
    0.73
    >';
    0.72
    OLA
    0.72
    iences
    0.72
    Activations Density 0.001%

    No Known Activations