© 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. 10-GEMMASCOPE-RES-131K
    7. 15653
    Prev
    Next
    INDEX
    Explanations

    binary string, image, search

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

    The neuron fires whenever it sees references to binary‐related data (e.g. “bin” or “binary”).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     have
    -1.37
    </h1>
    -1.34
    ◆◆
    -1.24
     wichtigsten
    -1.19
    ких
    -1.17
     {
    -1.14
                        
    -1.13
    andosi
    -1.08
     Entdecke
    -1.07
     pimiento
    -1.07
    POSITIVE LOGITS
     zda
    1.25
    ichteten
    1.20
     Kč
    1.17
    ০
    1.17
    üstet
    1.16
     елның
    1.16
    tiller
    1.15
    colnshire
    1.15
     Documentary
    1.14
    さんです
    1.14
    Activations Density 0.042%

    No Known Activations