© 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. 68928
    Prev
    Next
    INDEX
    Explanations

    programming keywords and functions

    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
     možná
    -1.00
     certamente
    -0.94
     الأحمر
    -0.88
     iconLine
    -0.87
     möglicherweise
    -0.85
    utm
    -0.84
    뚤
    -0.84
    idelberg
    -0.83
    美味しそう
    -0.81
     Bestandteil
    -0.80
    POSITIVE LOGITS
    AndGet
    1.84
     $-$
    0.90
    																		
    0.90
    getcwd
    0.89
    نوع
    0.87
    맛
    0.87
     terima
    0.85
     along
    0.85
    [-\
    0.85
    ✎
    0.83
    Activations Density 0.023%

    No Known Activations