© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6481
    Prev
    Next
    INDEX
    Explanations

    Python programming and math

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

    The neuron fires on uncommon, multi-syllable content words—particularly rare or specialized vocabulary across domains.

    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
    طار
    0.82
    را
    0.82
    鵠
    0.77
    туры
    0.76
    stantial
    0.76
    uddho
    0.75
    forcements
    0.75
    готовки
    0.75
    oncer
    0.74
     министер
    0.74
    POSITIVE LOGITS
     đị
    0.72
     wg
    0.70
     basalt
    0.67
     F
    0.67
     NOx
    0.66
    PER
    0.66
     weeds
    0.65
     xấu
    0.65
    th
    0.64
     dud
    0.64
    Activations Density 0.000%

    No Known Activations