© 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. 102141
    Prev
    Next
    INDEX
    Explanations

    code constructs and keywords

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

    whitespace or indentation at the beginning of lines in code.

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

    This neuron detects numeric literals (numbers) 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_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
    lgari
    -1.61
    泐
    -1.53
    енча
    -1.50
    iál
    -1.45
     naï
    -1.45
    ických
    -1.41
    ⅜
    -1.41
     laikā
    -1.39
    ۋ
    -1.38
     tog
    -1.36
    POSITIVE LOGITS
     for
    1.95
     in
    1.95
    -
    1.91
     In
    1.59
     here
    1.59
     because
    1.57
     When
    1.56
     there
    1.50
     either
    1.45
     into
    1.42
    Activations Density 0.012%

    No Known Activations