© 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. 22-GEMMASCOPE-RES-131K
    4. 73968
    Prev
    Next
    INDEX
    Explanations

    multi-lingual greetings and identifiers

    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_22/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
     its
    -1.09
    為に
    -1.08
    ponses
    -1.07
    様な
    -1.06
    _;
    
    -1.03
    łaj
    -0.99
    poň
    -0.97
    ueroa
    -0.94
    writeByte
    -0.94
    %)
    -0.93
    POSITIVE LOGITS
     Selanjutnya
    1.12
    还不错
    1.09
     preguntó
    1.05
     стихотво
    1.02
     Muchas
    1.02
    なので
    1.00
     Saludos
    1.00
     необхідно
    0.99
     geprüft
    0.97
     eccell
    0.95
    Activations Density 0.000%

    No Known Activations