© 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. 931
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily responds to numeric expressions (digits, numerical values, and decimal numbers).

    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
     and
    0.63
     -
    0.61
    ↵
    0.61
    1
    0.61
    ↵↵
    0.59
    0.58
    Ö
    0.58
    (?)
    0.57
    ö
    0.57
    2
    0.56
    POSITIVE LOGITS
     ampere
    0.69
     adenine
    0.68
    ⅽ
    0.67
    僮
    0.64
     populace
    0.64
     strolling
    0.62
     comparability
    0.62
     ἔ
    0.61
     seleccione
    0.61
     উত্প
    0.61
    Activations Density 1.570%

    No Known Activations