© 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. 22-GEMMASCOPE-RES-131K
    7. 73917
    Prev
    Next
    INDEX
    Explanations

    Q: question or The followed by utility/object/inference

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

    This neuron activates on C++ (and similar) namespace or class qualifiers using the scope‐resolution operator “::.”

    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
     then
    -1.32
    [
    -1.17
    ();
    -1.13
    ホイール
    -1.07
     just
    -1.02
     everyone
    -1.02
    然后
    -1.02
    чный
    -1.01
     no
    -1.00
    一隻
    -0.99
    POSITIVE LOGITS
     Wartawan
    1.33
    Wady
    1.20
     thép
    1.17
    われている
    1.16
    ihnachten
    1.12
    ⅝
    1.12
     CORRECT
    1.11
    TIA
    1.11
    ⅜
    1.11
    枚目
    1.09
    Activations Density 0.001%

    No Known Activations