© 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. 86495
    Prev
    Next
    INDEX
    Explanations

    code, lists, or titles following separators

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

    The neuron fires on code tokens associated with test assertions and UI-testing calls (e.g. “assertThat,” “Assertions,” “onView”).

    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
    ться
    -2.67
    媄
    -2.36
     vanguardia
    -2.34
    );
    -2.28
    おはよう
    -2.23
     теми
    -2.23
    𖡼
    -2.22
    黩
    -2.20
     joyería
    -2.19
    狲
    -2.19
    POSITIVE LOGITS
    {
    2.83
    ?
    2.77
    *
    2.59
    “
    2.30
    ments
    2.25
    al
    2.23
    .
    2.17
    asserole
    2.16
     “
    2.11
    '
    2.02
    Activations Density 0.000%

    No Known Activations