© 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. 2340
    Prev
    Next
    INDEX
    Explanations

    "it means that"

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

    This neuron detects numeric values (especially measurements, scores, and statistical figures).

    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
     prostu
    0.77
     đó
    0.70
     그걸
    0.67
     melakukannya
    0.67
    それを
    0.66
     We
    0.66
    しかも
    0.64
     المزيد
    0.63
     cioè
    0.62
     we
    0.62
    POSITIVE LOGITS
     during
    1.69
     although
    1.59
    虽然
    1.57
    雖然
    1.57
     خلال
    1.55
     katika
    1.55
     while
    1.50
     durante
    1.45
     trong
    1.42
    during
    1.41
    Activations Density 0.288%

    No Known Activations