© 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. 10-GEMMASCOPE-RES-131K
    7. 22118
    Prev
    Next
    INDEX
    Explanations

    words starting with peri

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

    This neuron strongly activates on words beginning with the prefix “per-” (e.g., peribullous, perioperative, perinuclear).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    '
    -3.20
    {
    -2.55
    "
    -2.19
    或
    -2.19
    );
    -2.16
    In
    -2.09
    ↵↵
    -2.09
     що
    -2.08
    "));
    -1.98
    [
    -1.98
    POSITIVE LOGITS
    臜
    2.42
    嚒
    2.31
    larda
    2.25
    缡
    2.19
    Πηγή
    2.16
    䨻
    2.13
    ſelves
    2.11
    llavero
    2.06
    َر
    2.06
     beyaz
    2.06
    Activations Density 0.031%

    No Known Activations