© 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. 6056
    Prev
    Next
    INDEX
    Explanations

    list/enumerated items

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

    The neuron fires on large numeric tokens—specifically floating-point or decimal numbers embedded 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
     UPC
    0.83
     Wentworth
    0.83
     Fernández
    0.80
    ﻳ
    0.80
     AWD
    0.80
     خانو
    0.79
     Barca
    0.79
     AsyncStorage
    0.79
    ы
    0.77
    ﺙ
    0.77
    POSITIVE LOGITS
    ри
    0.73
    ccess
    0.71
     cere
    0.69
     remise
    0.68
    urii
    0.68
     ense
    0.67
    ression
    0.65
    amburg
    0.64
     instru
    0.64
     remettre
    0.64
    Activations Density 0.000%

    No Known Activations