© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6918
    Prev
    Next
    INDEX
    Explanations

    special characters and technical queries

    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
    Not in Any Lists

    No Comments

    Negative Logits
     drogi
    -1.08
     möglichst
    -1.08
     разных
    -1.01
     bekannten
    -1.01
    icans
    -0.98
    ㅘ
    -0.94
     speziell
    -0.94
     takich
    -0.94
     різних
    -0.92
     trochu
    -0.90
    POSITIVE LOGITS
    Ű
    1.06
    URLException
    1.01
    Oacute
    0.96
    وردار
    0.96
    Iacute
    0.94
    RÉ
    0.94
     haar
    0.92
    ﻻ
    0.92
    ŵ
    0.92
    TagMode
    0.89
    Activations Density 0.020%

    No Known Activations