© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61386
    Prev
    Next
    INDEX
    Explanations

    "isn't" questions

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

    This neuron fires on the substring “Isn” (as in the contraction “Isn’t”) in the 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
    Конечно
    -2.92
     жовтня
    -2.88
    沺
    -2.83
    _
    -2.55
    んび
    -2.47
    viembre
    -2.47
     любить
    -2.47
     статті
    -2.44
    壟
    -2.42
     eerst
    -2.39
    POSITIVE LOGITS
    "
    4.44
     .
    2.59
     cataly
    2.30
     praktisch
    2.25
     sorprend
    2.25
    like
    2.23
    所有人都
    2.20
     «
    2.19
    \
    2.17
     incredibly
    2.16
    Activations Density 0.003%

    No Known Activations