© 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. 3768
    Prev
    Next
    INDEX
    Explanations

    i + or canal :

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

    This neuron detects decimal numbers (numeric values with a fractional part) in the text.

    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
    ഗ
    0.66
    พ
    0.65
     ہیں۔
    0.64
     ї
    0.64
    cam
    0.63
    増
    0.63
    Zara
    0.62
    cB
    0.61
    க
    0.61
    єш
    0.61
    POSITIVE LOGITS
     vicenda
    0.75
     neutrons
    0.73
    owment
    0.73
    miştir
    0.70
     shoreline
    0.68
    াবন
    0.68
    સી
    0.68
    inairement
    0.68
    ತ್ಮ
    0.68
     প্রতিরক্ষা
    0.68
    Activations Density 0.001%

    No Known Activations