© 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. 34-GEMMASCOPE-RES-131K
    7. 106565
    Prev
    Next
    INDEX
    Explanations

    unicode characters

    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
     took
    -1.20
     before
    -1.11
     get
    -1.00
     impressive
    -1.00
     during
    -0.96
     epitom
    -0.95
     for
    -0.95
     new
    -0.95
     this
    -0.93
     in
    -0.93
    POSITIVE LOGITS
     Cyril
    1.27
     Unicode
    1.25
     characters
    1.24
     unicode
    1.14
     character
    1.08
    
    1.07
    Karakter
    1.07
     trám
    1.06
     SPECIAL
    1.03
    characters
    1.03
    Activations Density 0.016%

    No Known Activations