© 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. 1639
    Prev
    Next
    INDEX
    Explanations

    This neuron specifically fires on unusually large numeric tokens (long numbers or floating-point values).

    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
    ﺘ
    0.87
    ا
    0.86
    ं
    0.84
    ת
    0.81
    ạ
    0.75
    біль
    0.75
    ن
    0.73
    ש
    0.73
    CTION
    0.72
    ை
    0.72
    POSITIVE LOGITS
     Rolle
    0.72
     actores
    0.71
     feng
    0.70
    logos
    0.68
     precios
    0.68
     andere
    0.67
     naciones
    0.67
    alchemy
    0.67
     asign
    0.66
    otheby
    0.66
    Activations Density 0.000%

    No Known Activations