© 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. 3920
    Prev
    Next
    INDEX
    Explanations

    code structure keywords

    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
     \
    -2.31
     on
    -2.19
     if
    -2.05
    じゃなくて
    -1.98
    ↵↵
    -1.90
     or
    -1.88
     in
    -1.84
    ↑↑↑</
    -1.84
     &
    -1.83
     ",";
    -1.83
    POSITIVE LOGITS
    泐
    2.20
    of
    2.14
    ’-
    2.09
     Auffassung
    2.08
    ?’
    2.08
    ,:
    2.06
    覿
    2.05
    糴
    2.02
    怱
    2.02
    without
    2.00
    Activations Density 0.001%

    No Known Activations