© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85303
    Prev
    Next
    INDEX
    Explanations

    technical abbreviations and code elements

    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
     without
    -1.75
     by
    -1.66
     with
    -1.59
     using
    -1.55
     until
    -1.51
     did
    -1.46
     like
    -1.43
    ↵
    -1.35
     不能
    -1.33
     before
    -1.30
    POSITIVE LOGITS
     of
    1.48
     unangemess
    1.38
    回目の
    1.36
     you
    1.36
    マジで
    1.34
    慢慢的
    1.28
     unbelievably
    1.23
     majestic
    1.23
    isés
    1.23
    ande
    1.23
    Activations Density 0.074%

    No Known Activations