© 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. 3317
    Prev
    Next
    INDEX
    Explanations

    sed commands

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

    This neuron activates on snippets of shell command‐line syntax—especially pipeline operators, grep invocations, and compiler or tool flags.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    уз
    0.50
     invál
    0.50
     Bakufu
    0.50
     Kabul
    0.49
    यूपी
    0.48
     defaul
    0.48
    UTC
    0.47
    adiq
    0.47
    apiKey
    0.47
    ("");
    0.46
    POSITIVE LOGITS
     arbej
    0.50
    ాల్సిన
    0.48
     Multiply
    0.48
    ابقة
    0.48
     이차
    0.48
     podmín
    0.47
     ज्या
    0.46
     ചില
    0.46
     بهذا
    0.46
    माइ
    0.45
    Activations Density 0.002%

    No Known Activations