© 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. 85472
    Prev
    Next
    INDEX
    Explanations

    whip

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

    This neuron fires on any form of the substring “whip” (e.g. whip, whipped, whiplash) regardless of context.

    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
    墒
    -2.56
     acutely
    -2.56
    珢
    -2.55
    秝
    -2.50
    ParameterLimits
    -2.50
     рецепта
    -2.41
    ”
    -2.41
    ⁛
    -2.34
    錨
    -2.34
    alakip
    -2.34
    POSITIVE LOGITS
    y
    2.73
    a
    2.72
    o
    2.39
    mäs
    2.39
     realizando
    2.25
     considerada
    2.23
    さぁ
    2.22
    鶺
    2.20
    ꦁ
    2.14
    ねぇ
    2.13
    Activations Density 0.001%

    No Known Activations