© 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. 2492
    Prev
    Next
    INDEX
    Explanations

    This neuron detects multi‐digit numeric tokens (especially years or other long number sequences).

    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
    මාන්
    0.79
    Subview
    0.79
     GQ
    0.79
     perdió
    0.77
     니
    0.77
     sospe
    0.76
     señaló
    0.75
    ゆっくり
    0.74
     (;
    0.74
     chắn
    0.73
    POSITIVE LOGITS
    स्ट
    0.70
    صل
    0.70
    要在
    0.70
    إن
    0.68
    豚
    0.68
    क्षात
    0.66
    క్ష
    0.66
    ↵
    0.64
    فتح
    0.64
    рити
    0.63
    Activations Density 0.000%

    No Known Activations