© 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. 14755
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly 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
    tt
    0.77
    ếm
    0.75
    :-
    0.71
     Hin
    0.69
    部門
    0.68
    da
    0.65
    SW
    0.64
     endors
    0.64
    cc
    0.64
     oath
    0.64
    POSITIVE LOGITS
     échanges
    0.78
     京都
    0.78
     cuisses
    0.77
     синте
    0.76
     significative
    0.74
    ഋ
    0.74
    ທີ່ມີ
    0.73
    ваме
    0.73
     classiques
    0.73
    bokeh
    0.72
    Activations Density 0.001%

    No Known Activations