© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34844
    Prev
    Next
    INDEX
    Explanations

    div class container and row

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

    The neuron strongly activates on occurrences of the string “container” (e.g. Bootstrap’s container class) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    かせる
    -1.50
     různých
    -1.48
     zwanzig
    -1.39
    vlá
    -1.27
     to
    -1.27
     marchio
    -1.27
    aussi
    -1.23
    seamnă
    -1.21
    <mask>
    -1.21
     也
    -1.20
    POSITIVE LOGITS
    礎
    1.16
    帮你
    1.16
    ここは
    1.16
    そこは
    1.13
    このように
    1.13
     adaptées
    1.11
     toep
    1.10
     actie
    1.10
     gena
    1.10
    すべての
    1.10
    Activations Density 0.002%

    No Known Activations