© 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. 34-GEMMASCOPE-RES-131K
    4. 118587
    Prev
    Next
    INDEX
    Explanations

    foreign words and country names

    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
    pearl
    -1.20
     FontWeight
    -0.98
     izin
    -0.98
    crimination
    -0.96
     என்
    -0.95
    ORUS
    -0.94
     pojaw
    -0.93
     pierwsze
    -0.91
     Fotografía
    -0.90
    ARON
    -0.89
    POSITIVE LOGITS
     vnder
    0.90
     auteurs
    0.88
    èl
    0.88
     schle
    0.87
     Sprung
    0.87
     urdu
    0.85
     satte
    0.83
    /%
    0.83
     Telefon
    0.82
     verru
    0.82
    Activations Density 0.007%

    No Known Activations