© 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. 2022
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on floating‐point numeric values (i.e. 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
    LogLevel
    0.72
    鿢
    0.71
    ReactNative
    0.70
    clientsdetails
    0.68
    Qa
    0.68
     Orphans
    0.65
    iOS
    0.64
    ais
    0.63
     निगम
    0.63
    ²',
    0.63
    POSITIVE LOGITS
     cuối
    0.65
     của
    0.63
     số
    0.63
     bạn
    0.62
     year
    0.60
     sử
    0.60
     đạt
    0.59
     nhất
    0.59
     peak
    0.57
     cít
    0.57
    Activations Density 0.005%

    No Known Activations