© 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. 129350
    Prev
    Next
    INDEX
    Explanations

    ky followed by specific suffixes

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

    The neuron fires on the specific character sequence “ky” (in any context or casing).

    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
    OUTUBE
    -2.84
    镚
    -2.52
    autorelease
    -2.39
    </sup>
    -2.34
    ing
    -2.31
    作って
    -2.25
     Many
    -2.25
     ihre
    -2.23
    a
    -2.23
     MUCH
    -2.20
    POSITIVE LOGITS
    ky
    3.63
    ’
    2.98
    ي
    2.97
    i
    2.77
    蹰
    2.73
    s
    2.64
    on
    2.48
    冧
    2.44
    autogui
    2.41
    our
    2.31
    Activations Density 0.006%

    No Known Activations