© 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. 79442
    Prev
    Next
    INDEX
    Explanations

    extending or running cables

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

    The neuron fires on domain-specific technical jargon (specialized nouns and verbs you’d find in how-to or engineering-style explanations).

    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
    斛
    -0.82
     cuaderno
    -0.78
    ONESIA
    -0.77
    ContextHolder
    -0.77
    mink
    -0.76
    HandlerContext
    -0.76
    맞
    -0.75
     пови
    -0.75
    ישראל
    -0.75
    úp
    -0.74
    POSITIVE LOGITS
     extending
    2.02
     extend
    1.92
    Extend
    1.82
     Extend
    1.71
     extension
    1.70
     Extending
    1.56
     extended
    1.55
     extensions
    1.55
    extend
    1.47
     протя
    1.47
    Activations Density 0.061%

    No Known Activations