© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60273
    Prev
    Next
    INDEX
    Explanations

    state of Delaware

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

    The neuron detects mentions of Delaware as a place or jurisdiction in document 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_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
    .
    -2.36
     it
    -1.58
     elbise
    -1.56
     otras
    -1.55
     gesund
    -1.55
    malıdır
    -1.54
    ⩖
    -1.50
    中午
    -1.48
     dringend
    -1.46
     stamps
    -1.45
    POSITIVE LOGITS
    了一种
    1.77
    օ
    1.77
     vinil
    1.73
    Благодаря
    1.71
     marmor
    1.69
    但她
    1.68
     برای
    1.68
    attare
    1.67
    ‪.‬‬
    1.66
     parlamento
    1.66
    Activations Density 0.009%

    No Known Activations