© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6894
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to numeric tokens (numbers, especially those with digits and decimal points).

    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_31_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
    }}}}
    0.54
     kojima
    0.50
    ※
    0.50
    Track
    0.49
    Run
    0.49
    IRT
    0.49
    lasting
    0.49
     આવા
    0.48
    )$
    0.48
    )\|
    0.48
    POSITIVE LOGITS
     cupcakes
    0.80
     meninas
    0.75
     _____
    0.73
     کے
    0.72
     ______
    0.72
     elever
    0.72
     hamburgers
    0.69
     ABSORBED
    0.68
     နှင့်
    0.67
     manzanas
    0.67
    Activations Density 0.063%

    No Known Activations