© 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. 60904
    Prev
    Next
    INDEX
    Explanations

    dates following "date:"

    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
     are
    -1.31
    如何在
    -1.28
     femeninos
    -1.27
     into
    -1.26
    niger
    -1.21
     legno
    -1.21
    大幅
    -1.13
    腋
    -1.11
    PAH
    -1.11
     is
    -1.10
    POSITIVE LOGITS
     ataupun
    1.50
     this
    1.45
     Mungkin
    1.32
     they
    1.32
    柃
    1.30
     Apabila
    1.27
     Eccle
    1.27
     if
    1.27
    ｙ
    1.23
     selepas
    1.21
    Activations Density 0.081%

    No Known Activations