© 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. 22-GEMMASCOPE-RES-131K
    7. 12407
    Prev
    Next
    INDEX
    Explanations

    code, commands, and technical terms

    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
     all
    -1.66
     you
    -1.59
     even
    -1.59
    直至
    -1.47
     on
    -1.38
     fase
    -1.34
     have
    -1.33
     are
    -1.31
    延长
    -1.30
     should
    -1.26
    POSITIVE LOGITS
     rassemb
    1.65
    Gön
    1.36
     bewertet
    1.35
     débar
    1.32
    ݯ
    1.31
     gurus
    1.30
     gezogen
    1.27
     présenter
    1.27
     zubehör
    1.27
    ctor
    1.27
    Activations Density 0.000%

    No Known Activations