© 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. 103975
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

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

    commas followed by a space or quote in programming code contexts.

    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
    ↵
    -3.13
     kumar
    -2.13
    ﮑ
    -2.06
     mein
    -1.87
    蔸
    -1.86
    地说
    -1.85
    ↑↑↑</
    -1.85
    沇
    -1.84
     bús
    -1.84
    屺
    -1.80
    POSITIVE LOGITS
    _
    2.30
     revamp
    2.13
     
    2.06
     

    2.05
     reaffirm
    2.05
     Commonly
    2.00
    WHAT
    2.00
     Еще
    1.94
     lessen
    1.91
     humiliating
    1.88
    Activations Density 0.001%

    No Known Activations