© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10516
    Prev
    Next
    INDEX
    Explanations

    in the context of

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

    The neuron is activated by numeric tokens—especially 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
     the
    0.78
    કિંગ
    0.75
    倜
    0.69
    ersonic
    0.68
     groin
    0.67
     данным
    0.66
    Problem
    0.63
    izing
    0.63
    the
    0.62
     Davis
    0.62
    POSITIVE LOGITS
    d
    0.73
    뭐
    0.71
    ของการ
    0.70
    lisi
    0.70
    ઓ
    0.70
     mehrerer
    0.70
    هایی
    0.69
    dz
    0.68
    dır
    0.66
     memutuskan
    0.65
    Activations Density 0.072%

    No Known Activations