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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49016
    Prev
    Next
    INDEX
    Explanations

    toxicity, ultimatum, immune, PUBLICATION

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

    programming or technical document elements such as variable names, code syntax, and formatting identifiers.

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

    The neuron strongly activates on isolated technical identifiers or acronyms (i.e. tokens in code, headings, or “ALL-CAPS” terms).

    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
     simulate
    -0.81
     Cur
    -0.81
     well
    -0.75
     may
    -0.75
     матери
    -0.74
    czyn
    -0.73
     guide
    -0.73
     other
    -0.73
     accounting
    -0.73
     Ann
    -0.72
    POSITIVE LOGITS
    üe
    0.93
     Atas
    0.86
    takings
    0.84
     moteurs
    0.84
    Coca
    0.84
     diamants
    0.83
     CANCER
    0.83
    ߖ
    0.82
    valuation
    0.81
    ℗
    0.81
    Activations Density 0.001%

    No Known Activations