© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2321
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on floating‐point number tokens (decimal numbers).

    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
    ను
    1.09
     статей
    0.96
    ي
    0.95
    িয়াছিল
    0.87
    ERICK
    0.85
     successivement
    0.84
    нг
    0.84
    uerite
    0.82
    elbe
    0.81
     fluores
    0.80
    POSITIVE LOGITS
    ’
    0.89
    居住
    0.89
     দেড়
    0.86
    います
    0.86
    𝓀
    0.82
    境
    0.81
     sót
    0.80
    いる
    0.79
    getPopulation
    0.79
    呐
    0.79
    Activations Density 0.005%

    No Known Activations