© 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. 22-GEMMASCOPE-RES-131K
    7. 64628
    Prev
    Next
    INDEX
    Explanations

    questions and code snippets

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

    The neuron fires on numeric literals (integer or floating‐point constants) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ayrıca
    -1.11
     början
    -1.10
     trám
    -1.07
     specialmente
    -1.06
    productos
    -1.02
     respectivos
    -0.99
     például
    -0.97
    somebody
    -0.96
     somebody
    -0.96
     someone
    -0.92
    POSITIVE LOGITS
     if
    1.21
    If
    1.05
     любом
    0.96
    <h2>
    0.94
    "?
    0.93
    >
    0.93
     If
    0.90
    当店
    0.88
     unbeaten
    0.87
    kipun
    0.85
    Activations Density 0.000%

    No Known Activations