© 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. 120094
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming terms

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

    code blocks or indented sections in technical/programming documents.

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

    The neuron fires on long runs of whitespace (indentation or large blank-space spans) in code or text.

    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
     it
    -2.06
    s
    -1.83
     can
    -1.82
     has
    -1.78
     puts
    -1.76
     not
    -1.69
     gave
    -1.68
     makes
    -1.67
     could
    -1.61
     It
    -1.59
    POSITIVE LOGITS
    <>
    
    1.95
     ۵
    1.89
    }();
    1.89
    鹩
    1.84
    dienne
    1.81
     ſtate
    1.80
     ſtand
    1.80
    '},
    1.77
     juſ
    1.76
     vrou
    1.74
    Activations Density 0.109%

    No Known Activations