© 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. 67721
    Prev
    Next
    INDEX
    Explanations

    academic citations and code

    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
     from
    -1.57
     if
    -1.31
     in
    -1.20
     by
    -1.16
     process
    -1.09
     проблеми
    -1.09
     rate
    -1.07
     ثم
    -1.05
     ensure
    -1.05
     on
    -1.02
    POSITIVE LOGITS
     céu
    1.48
     feltro
    1.45
     segredo
    1.35
     maravilhoso
    1.34
     cinza
    1.32
     interessantes
    1.32
     aço
    1.30
     ótimo
    1.30
     prêmio
    1.28
     folhe
    1.27
    Activations Density 0.000%

    No Known Activations