© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62468
    Prev
    Next
    INDEX
    Explanations

    RGraph charting library code

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

    The neuron activates on code-like tokens—especially JavaScript identifiers, keywords, numbers, and symbols—i.e. snippets of JS code.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    キシ
    -0.88
    Personensuche
    -0.79
     podoba
    -0.78
    รับ
    -0.77
     pelajar
    -0.75
    rowy
    -0.74
    rollen
    -0.73
    meanor
    -0.73
    ATUM
    -0.73
    蒻
    -0.73
    POSITIVE LOGITS
    notFound
    0.79
    inOrder
    0.78
     Damas
    0.74
    jvm
    0.73
     くん
    0.71
     들어
    0.70
     géographie
    0.70
     Deus
    0.69
    Secondo
    0.69
     {{{
    0.69
    Activations Density 0.013%

    No Known Activations