© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106122
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     better
    -1.05
     بهتر
    -0.92
     represented
    -0.89
     også
    -0.88
     bathed
    -0.85
     juega
    -0.84
     също
    -0.84
    =_
    -0.84
     definitively
    -0.83
     gewal
    -0.83
    POSITIVE LOGITS
     accompagner
    0.97
    artney
    0.96
    ideal
    0.94
     спортс
    0.94
    ainen
    0.91
     серии
    0.89
     grosse
    0.89
    杆
    0.88
     spécialement
    0.86
    عات
    0.85
    Activations Density 0.032%

    No Known Activations