© 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. 39566
    Prev
    Next
    INDEX
    Explanations

    code components and keywords

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

    The neuron fires on occurrences of a double‐underscore sequence (__) within code identifiers.

    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
     provocando
    -2.36
    ”。
    -2.31
    🫣
    -2.23
    Ꮏ
    -2.22
     is
    -2.22
    鼷
    -2.16
    孓
    -2.06
    🫶
    -2.02
     or
    -2.00
    可能的
    -2.00
    POSITIVE LOGITS
    [
    3.23
    ?
    2.50
    1
    2.36
    (
    2.34
    {
    2.27
    庒
    2.27
     salão
    2.22
    *
    2.17
    ي
    2.17
    ,.
    2.14
    Activations Density 0.014%

    No Known Activations