© 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. 5519
    Prev
    Next
    INDEX
    Explanations

    not final, not fatal

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

    The neuron fires on numeric tokens representing decimal or floating‐point values.

    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
     اظهار
    0.61
     تخص
    0.55
    ToDO
    0.55
     کاز
    0.54
    ክር
    0.52
    䒴
    0.52
    你应该
    0.50
    大陆
    0.50
     सापेक्ष
    0.49
     viss
    0.49
    POSITIVE LOGITS
     Noyes
    0.56
    pol
    0.54
     Lauderdale
    0.54
    യെ
    0.51
    SIBLE
    0.51
     briefly
    0.50
     Spencer
    0.50
    ienta
    0.49
    蓋
    0.49
     Lake
    0.48
    Activations Density 0.002%

    No Known Activations