© 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. 22-GEMMASCOPE-RES-131K
    4. 39859
    Prev
    Next
    INDEX
    Explanations

    programming variables and common code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     so
    -1.09
     it
    -1.05
     from
    -0.95
     what
    -0.90
     here
    -0.88
     caminha
    -0.88
     if
    -0.86
     which
    -0.85
     reconnu
    -0.85
     Turm
    -0.84
    POSITIVE LOGITS
     نیز
    1.05
     alfo
    1.00
     também
    0.98
     Xerox
    0.98
     גם
    0.97
     MOU
    0.97
     همان
    0.96
     flamb
    0.94
     chibi
    0.94
    рем
    0.93
    Activations Density 0.004%

    No Known Activations