© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9536
    Prev
    Next
    INDEX
    Explanations

    @id, AS, text

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

    The neuron activates on numeric tokens—especially floating-point numbers or other multi-digit figures.

    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
     Шрифт
    0.81
     テ
    0.80
     Бү
    0.80
     Фа
    0.73
     Feather
    0.73
     سقوط
    0.73
     Коло
    0.72
     فن
    0.71
     ピ
    0.71
     ład
    0.71
    POSITIVE LOGITS
    from
    0.87
    by
    0.84
    with
    0.82
    via
    0.75
                   
    0.72
    0.71
     sexes
    0.70
                     
    0.70
     thru
    0.70
                    
    0.68
    Activations Density 0.001%

    No Known Activations