© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102432
    Prev
    Next
    INDEX
    Explanations

    XML and HTML code snippets

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

    the opening tag of a block or container element in structured code (like `<tbody>`, namespace declarations, or code blocks).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on lines that begin with substantial leading whitespace (i.e. indented code or nested markup).

    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
     вернулся
    -1.62
     санкт
    -1.50
     鍋
    -1.47
    无比
    -1.41
    哢
    -1.38
    得到的
    -1.36
     PROCEEDINGS
    -1.35
     揚げ
    -1.34
     LIRE
    -1.34
    AutoModerator
    -1.32
    POSITIVE LOGITS
    ry
    1.73
     outright
    1.61
    uspiel
    1.59
     maximizing
    1.59
    ni
    1.59
    ek
    1.59
    na
    1.56
     adventures
    1.54
    寥
    1.53
    vosti
    1.49
    Activations Density 0.001%

    No Known Activations