© 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. 68810
    Prev
    Next
    INDEX
    Explanations

    comma followed by conjunction

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

    The neuron fires strongly on tokens referring to medical/injury contexts—especially mentions of equipment (e.g. “walker”), procedures (e.g. “MRI”), and physical pain or recovery.

    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
    '>"
    -1.34
    —“
    -1.32
    ग़
    -1.30
    zestaw
    -1.26
    --"
    -1.26
    hubanes
    -1.25
    —"
    -1.23
    AHUL
    -1.23
    蕖
    -1.20
    饪
    -1.18
    POSITIVE LOGITS
     I
    2.13
     [
    2.08
     so
    1.70
     we
    1.66
     there
    1.56
    ,”
    1.52
     they
    1.48
    </strong>
    1.44
     and
    1.42
     {
    1.35
    Activations Density 0.011%

    No Known Activations