© 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. 90431
    Prev
    Next
    INDEX
    Explanations

    scientific papers and preprints

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

    URLs and document identifiers in scientific papers, particularly arXiv references.

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

    The neuron is tuned to spotting multi‐digit numeric identifiers (e.g. report numbers, arXiv IDs, page or section numbers) in the 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
    either
    -0.81
    casm
    -0.80
    лах
    -0.78
    readFileSync
    -0.77
     aforementioned
    -0.77
     article
    -0.76
     ouverts
    -0.76
     competitively
    -0.75
    したのは
    -0.75
    schemas
    -0.75
    POSITIVE LOGITS
    vVar
    0.88
    Mimi
    0.85
     доб
    0.84
     ceux
    0.84
     velg
    0.84
     Trot
    0.83
    áticos
    0.82
    Rohan
    0.80
     Mimi
    0.79
     négo
    0.78
    Activations Density 0.004%

    No Known Activations