© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5276
    Prev
    Next
    INDEX
    Explanations

    border, required, padding

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

    The neuron primarily detects question‐mark punctuation.

    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
     일반적으로
    0.54
     Conversely
    0.53
     Revenue
    0.52
     Legislation
    0.50
     Endless
    0.50
     은
    0.50
    ।
    0.50
     Books
    0.49
     dọc
    0.49
     Peace
    0.48
    POSITIVE LOGITS
     enlace
    0.61
     susah
    0.59
     intelig
    0.58
     नांद
    0.56
    lingu
    0.53
    氻
    0.53
    marginBottom
    0.53
    TextAlign
    0.52
     llevaba
    0.52
    cooling
    0.52
    Activations Density 0.012%

    No Known Activations