© 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. 110923
    Prev
    Next
    INDEX
    Explanations

    code constructs

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

    the word "code" in technical programming contexts, especially when discussing shortcodes, bytecode, or code-related programming terms.

    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
    她
    -1.81
    ’
    -1.79
    iencia
    -1.52
    而
    -1.52
    这里
    -1.48
    了
    -1.46
    这种
    -1.41
    ﹅
    -1.41
    这些
    -1.40
    大家好
    -1.40
    POSITIVE LOGITS
    ܜ
    1.78
     each
    1.73
    lgari
    1.59
     следующем
    1.52
            
    1.51
     their
    1.51
     your
    1.50
     the
    1.49
     exploits
    1.48
    dza
    1.48
    Activations Density 0.007%

    No Known Activations