© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34004
    Prev
    Next
    INDEX
    Explanations

    medical and data analysis contexts

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

    medical and scientific terms or topics in academic or research documents.

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

    The neuron is triggered by numeric and data-related tokens—especially digits, dataset sizes, and count figures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     in
    -1.59
     or
    -1.50
     without
    -1.40
     this
    -1.34
     if
    -1.27
     until
    -1.27
     氏
    -1.23
     requires
    -1.20
     immediately
    -1.16
     when
    -1.15
    POSITIVE LOGITS
     pâtes
    1.34
     fizeram
    1.34
     estavam
    1.28
     ficaram
    1.19
     saveurs
    1.18
     montrent
    1.13
     venant
    1.12
    ματος
    1.11
    Rad
    1.11
    Yang
    1.10
    Activations Density 0.011%

    No Known Activations