© 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. 47675
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers

    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
    嫫
    -1.35
    
    -1.29
     zároveň
    -1.28
    оо
    -1.27
     You
    -1.26
     or
    -1.23
     Biologie
    -1.23
     mondta
    -1.22
    árs
    -1.21
    детская
    -1.21
    POSITIVE LOGITS
     few
    1.44
     wersji
    1.33
     little
    1.27
    圌
    1.27
    sweise
    1.26
    狷
    1.24
    Understand
    1.23
     swój
    1.23
    somewhat
    1.21
     premières
    1.19
    Activations Density 0.018%

    No Known Activations