© 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. 7261
    Prev
    Next
    INDEX
    Explanations

    aspect ratio parameter

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

    The neuron fires on floating‐point numeric tokens (numbers with decimal points).

    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
    するという
    0.90
    ваны
    0.89
    рованы
    0.85
    та
    0.84
    に対して
    0.84
    橐
    0.83
     ferramentas
    0.82
     carreteras
    0.82
    闾
    0.82
    ﭥ
    0.82
    POSITIVE LOGITS
     administrator
    0.73
     ابي
    0.68
     القيام
    0.68
     Administrator
    0.66
     V
    0.66
     دار
    0.66
    ни
    0.65
     Music
    0.65
    гли
    0.65
    craft
    0.64
    Activations Density 0.001%

    No Known Activations