© 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. 22-GEMMASCOPE-RES-131K
    7. 13394
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

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

    technical terms in scientific, technical, or programming documents.

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

    The neuron is activated by numeric tokens (numbers and numeric values) 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_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
     which
    -1.23
    ところに
    -1.19
     between
    -1.16
     or
    -1.06
     at
    -1.03
     of
    -1.03
    よろ
    -1.02
    所で
    -1.00
     like
    -0.98
    のではなく
    -0.94
    POSITIVE LOGITS
     but
    1.31
     ''){
    1.10
     másik
    1.09
     แต่
    1.02
    upported
    0.99
     امکان
    0.98
    wendi
    0.96
     nhưng
    0.95
    oczes
    0.95
    อื่น
    0.94
    Activations Density 0.022%

    No Known Activations