© 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. 2035
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens—especially floating‐point numbers or multi‐digit figures.

    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
    ك
    0.91
    य
    0.89
     fiel
    0.84
     Віль
    0.81
     Focused
    0.80
    ش
    0.79
    كيل
    0.79
     complesso
    0.78
    ي
    0.77
     Și
    0.76
    POSITIVE LOGITS
     каждом
    0.84
     соревнования
    0.83
     turbocharged
    0.81
     quarterbacks
    0.79
     blouses
    0.75
     tomando
    0.74
     outboard
    0.73
     strokeWeight
    0.73
    ваты
    0.73
     effluents
    0.73
    Activations Density 0.000%

    No Known Activations