© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84563
    Prev
    Next
    INDEX
    Explanations

    high followed by specific adjectives

    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_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
      
    -2.36
    -
    -2.02
    dersfield
    -1.96
     somewhat
    -1.95
     эффектив
    -1.95
     frequentemente
    -1.95
     have
    -1.91
     häufigsten
    -1.89
     largely
    -1.87
     pequena
    -1.86
    POSITIVE LOGITS
    ୌ
    2.33
     errori
    2.17
    s
    2.16
     ediyor
    2.11
    ﻊ
    2.09
     miliardi
    1.98
     vicino
    1.97
    VolleyError
    1.95
     perawatan
    1.95
    ﹑
    1.95
    Activations Density 0.023%

    No Known Activations