© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10720
    Prev
    Next
    INDEX
    Explanations

    translation, dosage, numbers

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

    The neuron fires on metadata labels—particularly category and tag names—rather than regular article 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
     pero
    0.90
     but
    0.79
     maar
    0.78
     BUT
    0.74
     لكن
    0.74
     Pero
    0.73
     लेकिन
    0.69
     但
    0.66
     mutta
    0.65
    前に
    0.64
    POSITIVE LOGITS
     Çünkü
    0.73
     защото
    0.73
    Vì
    0.71
    Tổng
    0.71
     zbog
    0.70
    constraintTop
    0.70
     wśród
    0.70
    Todas
    0.69
    他又
    0.69
     vì
    0.68
    Activations Density 0.086%

    No Known Activations