© 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. 47175
    Prev
    Next
    INDEX
    Explanations

    questions or headings

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

    The neuron activates on dictionary‐style entries—numbered senses, pronunciation keys, part‐of‐speech labels, and gloss formatting.

    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
    erencia
    -0.82
    ->$
    -0.79
    liath
    -0.78
    maxn
    -0.77
     narrator
    -0.77
    haraan
    -0.75
    ::~
    -0.75
    ⚄
    -0.75
    🧰
    -0.75
    toare
    -0.75
    POSITIVE LOGITS
    жу
    0.83
     ennen
    0.81
    Save
    0.80
    SAVE
    0.80
     history
    0.77
    PERT
    0.76
     Save
    0.76
     அவ
    0.75
    bilder
    0.75
     ریزی
    0.73
    Activations Density 0.009%

    No Known Activations