© 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. 11278
    Prev
    Next
    INDEX
    Explanations

    between start and end coordinates

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

    This neuron activates on numeric values (especially decimal or floating‐point numbers) in technical 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_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
    I
    0.27
    C
    0.26
    2
    0.25
    3
    0.25
    J
    0.25
    0.25
    P
    0.25
    L
    0.25
    V
    0.24
    W
    0.24
    POSITIVE LOGITS
     anastomosis
    0.27
     anastom
    0.26
     multilateral
    0.26
     hemod
    0.25
     acidosis
    0.25
     działal
    0.24
     sinusoid
    0.24
     deň
    0.24
     dá
    0.24
     dużo
    0.24
    Activations Density 0.031%

    No Known Activations