© 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. 110891
    Prev
    Next
    INDEX
    Explanations

    wrapper class or id

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

    The neuron fires specifically on occurrences of the token “wrapper,” i.e. when HTML elements are given a class or id of “wrapper.”

    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
    蹰
    -2.83
     unſ
    -2.66
     supper
    -2.44
    ⃑
    -2.42
    ଝ
    -2.36
    ᯾
    -2.33
    釙
    -2.27
     expuls
    -2.25
    苤
    -2.25
     cinque
    -2.23
    POSITIVE LOGITS
    л
    2.56
     Since
    2.33
    er
    2.25
     accordance
    2.25
     During
    2.19
    replyreport
    2.19
     Ideally
    2.14
     =
    2.11
    A
    2.11
    ).
    2.09
    Activations Density 0.002%

    No Known Activations