© 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. 9410
    Prev
    Next
    INDEX
    Explanations

    Calculator Test

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

    The neuron is selectively activated by numeric quantities or measurements (e.g. amounts, counts, sizes, dosages).

    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
    opak
    0.52
    ovascular
    0.51
    捜
    0.50
     longed
    0.50
    ᵕ
    0.49
     ।,
    0.49
    ócio
    0.49
    oski
    0.49
    ípios
    0.48
     रैंकिंग
    0.48
    POSITIVE LOGITS
     ==
    0.65
     =
    0.61
    ==
    0.58
     teken
    0.57
     castillo
    0.52
    =
    0.52
    =[
    0.51
     ===
    0.51
     Mott
    0.51
     yaitu
    0.50
    Activations Density 0.000%

    No Known Activations