© 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. 64670
    Prev
    Next
    INDEX
    Explanations

    Anterior cruciate ligament

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

    numerical values and percentages in technical or scientific documents.

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

    The neuron fires on uppercase alphanumeric labels and headings—especially shipping‐hazard classification codes (e.g. “Biological Substances Category B,” “2.2,” “7”).

    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
     manna
    -0.80
     petro
    -0.80
     Peaceful
    -0.77
     unprepared
    -0.77
     obverse
    -0.76
     acci
    -0.71
     jamb
    -0.69
    TestBase
    -0.69
     Stip
    -0.68
     agi
    -0.68
    POSITIVE LOGITS
     NOS
    0.89
    gner
    0.88
    klasse
    0.85
    ocrat
    0.84
     Hayden
    0.83
    etted
    0.82
    zoeken
    0.81
     technische
    0.81
     Trennung
    0.80
     Bayley
    0.77
    Activations Density 0.017%

    No Known Activations