© 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. 1383
    Prev
    Next
    INDEX
    Explanations

    locations and institutions

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

    The neuron primarily activates on decimal numbers (i.e. numeric tokens containing a period).

    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
     стихо
    0.59
    farbe
    0.54
     песен
    0.54
    buttonclick
    0.52
     analyte
    0.52
    prechen
    0.52
    
    0.52
     смер
    0.51
    ្អ
    0.50
    resposta
    0.50
    POSITIVE LOGITS
     National
    0.67
     Northern
    0.65
     South
    0.64
     K
    0.62
     North
    0.61
     B
    0.59
     G
    0.59
     University
    0.59
     Maritime
    0.59
     Regional
    0.58
    Activations Density 0.001%

    No Known Activations