© 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. 129256
    Prev
    Next
    INDEX
    Explanations

    This neuron detects two-letter grid position labels (e.g. TL, TR, BL, BR, MM) in a matrix representation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numerical sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    tico
    -0.82
    erry
    -0.78
    خان
    -0.77
    Aa
    -0.77
    flake
    -0.77
     Wier
    -0.77
     רק
    -0.76
    heri
    -0.76
     Ngh
    -0.75
    rmtree
    -0.75
    POSITIVE LOGITS
    体力
    0.84
    왓
    0.82
    evaluator
    0.77
    selectBy
    0.76
    '])){
    0.76
     Louvre
    0.75
    ểu
    0.75
    ֣
    0.75
    izm
    0.74
     fakty
    0.73
    Activations Density 0.042%

    No Known Activations