© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6913
    Prev
    Next
    INDEX
    Explanations

    Live Imaging

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

    technical patent or legal document text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is specialized for detecting the word “shaving” (as it appears repeatedly in the patent-style text).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Klang
    -0.85
    ühen
    -0.84
     incipient
    -0.84
    Manila
    -0.83
    散文
    -0.82
    Faust
    -0.82
     extracurricular
    -0.81
    WebServlet
    -0.81
    andria
    -0.77
     lucky
    -0.76
    POSITIVE LOGITS
     rechargeable
    0.94
     Sonic
    0.88
     Wet
    0.87
     Cleaning
    0.87
     Chronic
    0.85
     Pix
    0.83
    Sonic
    0.83
     cordless
    0.82
     sonic
    0.81
    Cleaning
    0.81
    Activations Density 0.004%

    No Known Activations