© 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. 11185
    Prev
    Next
    INDEX
    Explanations

    Weekly structure

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

    This neuron responds to formatting and structural tokens—spaces, punctuation marks, symbols, and other non-word layout elements.

    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
     mouth
    0.72
    口
    0.71
     Mouth
    0.69
    mouth
    0.66
     mouths
    0.62
    未知
    0.61
    ່ຽ
    0.61
    口的
    0.56
    嘴
    0.55
    口腔
    0.53
    POSITIVE LOGITS
     eee
    0.91
     ee
    0.83
     ae
    0.79
     oe
    0.74
     =)
    0.68
     ake
    0.64
     ——
    0.60
     Eee
    0.60
     Oo
    0.60
     emer
    0.60
    Activations Density 0.008%

    No Known Activations