© 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. 101587
    Prev
    Next
    INDEX
    Explanations

    code elements

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

    blank lines or whitespace-only lines in code that separate logical sections of a program.

    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
     był
    -1.98
    0
    -1.81
    provides
    -1.80
    became
    -1.72
    usually
    -1.70
    could
    -1.69
     hace
    -1.68
            
    -1.67
      
    -1.67
     podría
    -1.65
    POSITIVE LOGITS
     it
    2.38
     from
    2.03
     sement
    1.66
     mola
    1.66
     doraemon
    1.62
     combusti
    1.61
     banan
    1.60
     waifu
    1.60
     pneu
    1.59
     graden
    1.59
    Activations Density 0.006%

    No Known Activations