© 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. 11560
    Prev
    Next
    INDEX
    Explanations

    This neuron strongly activates on numeric tokens (i.e. standalone numbers or decimal‐number strings).

    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
     জন্যও
    0.81
    ،
    0.73
     জন্য
    0.67
     ub
    0.67
     onder
    0.65
     tra
    0.64
    こともある
    0.63
     l
    0.62
    L
    0.62
     sabot
    0.61
    POSITIVE LOGITS
     ISNI
    0.82
     ভাষার
    0.79
     elastomers
    0.79
    ▶
    0.78
    갤럭
    0.77
     adhesives
    0.77
    억
    0.77
     大学
    0.75
     rougeâtres
    0.75
     顔
    0.75
    Activations Density 0.000%

    No Known Activations