© 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. 100107
    Prev
    Next
    INDEX
    Explanations

    wallet, purse, pocket

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

    The neuron activates on occurrences of the word “wallet.”

    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
    НЫЕ
    -1.83
     vea
    -1.81
    borderSide
    -1.73
     estatua
    -1.61
    фран
    -1.55
     ſont
    -1.55
    ето
    -1.55
    🇳
    -1.55
    СКИ
    -1.53
    oxidase
    -1.50
    POSITIVE LOGITS
     steadfast
    1.72
    d
    1.63
    the
    1.57
    '
    1.54
     財布
    1.45
    \
    1.41
    lcccccc
    1.35
     AND
    1.34
     impegn
    1.34
     murky
    1.33
    Activations Density 0.003%

    No Known Activations