© 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. 12354
    Prev
    Next
    INDEX
    Explanations

    language-specific syntax inside code blocks

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

    whitespace indentation at the beginning of lines in source code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    任何
    -1.73
    ława
    -1.69
    你的
    -1.65
    她的
    -1.54
    昨天
    -1.53
     zrobić
    -1.52
    它的
    -1.52
    IALE
    -1.49
    它是
    -1.49
    他的
    -1.49
    POSITIVE LOGITS
    .
    1.81
     and
    1.79
    when
    1.73
    Because
    1.57
    there
    1.55
    because
    1.52
    When
    1.51
     because
    1.43
     first
    1.39
     apostar
    1.37
    Activations Density 0.092%

    No Known Activations