© 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. 769
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numerical tokens formatted as decimal (floating‐point) 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
    śred
    0.37
    哒
    0.35
    daw
    0.33
     Są
    0.33
    <unused2186>
    0.32
    acruz
    0.32
    dari
    0.32
     Chargers
    0.31
     있다면
    0.31
    𝑑
    0.31
    POSITIVE LOGITS
     behalf
    0.38
     endast
    0.38
     whom
    0.35
    '
    0.34
     tomto
    0.34
     mocy
    0.34
    .
    0.32
     mehreren
    0.32
     podstawie
    0.31
     consigue
    0.31
    Activations Density 0.000%

    No Known Activations