© 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. 10-GEMMASCOPE-RES-131K
    4. 11752
    Prev
    Next
    INDEX
    Explanations

    foreign language and expressive punctuation

    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
     our
    -1.89
    ଶ
    -1.75
     who
    -1.75
    </strong>
    -1.70
     również
    -1.59
     এবং
    -1.59
    . 
    -1.57
     are
    -1.55
    anız
    -1.48
    -1.44
    POSITIVE LOGITS
     Mungkin
    1.62
     Fuerzas
    1.60
     Bagaimana
    1.60
     Beſ
    1.56
    😵
    1.55
     عاشقانه
    1.55
    Belum
    1.50
     هناك
    1.48
     ¡¡
    1.48
    شير
    1.47
    Activations Density 0.058%

    No Known Activations