© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86918
    Prev
    Next
    INDEX
    Explanations

    tug, tugged, tugs

    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
    ஂ
    -2.61
    呖
    -2.52
     после
    -2.48
     شیپور
    -2.48
    豨
    -2.42
     judíos
    -2.36
     mago
    -2.36
    Otro
    -2.34
    蹋
    -2.34
     میکن
    -2.33
    POSITIVE LOGITS
    1
    2.69
    銠
    2.55
     Quando
    2.50
     enmar
    2.45
     respald
    2.39
     diseñ
    2.31
    ;
    2.28
     empê
    2.25
     
    2.23
    the
    2.22
    Activations Density 0.003%

    No Known Activations