© 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. 24-GEMMASCOPE-2-RES-16K
    7. 10020
    Prev
    Next
    INDEX
    Explanations

    two known values

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is tuned to spot numeric tokens (numbers and numerical expressions) in the text.

    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
     vielfält
    0.66
    +\|\
    0.64
    新たに
    0.63
    നില
    0.61
     ವಿವಿಧ
    0.60
    ONSE
    0.59
    EPEND
    0.59
     enviados
    0.58
    种种
    0.58
    OUTH
    0.57
    POSITIVE LOGITS
     two
    0.67
    Two
    0.67
    店
    0.67
     deux
    0.66
    But
    0.66
    是很
    0.65
    侑
    0.64
     three
    0.64
    Very
    0.64
    For
    0.63
    Activations Density 0.000%

    No Known Activations