© 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. 11156
    Prev
    Next
    INDEX
    Explanations

    parentheses, quotes, or abbreviations

    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
     in
    -1.89
     now
    -1.67
     even
    -1.64
     these
    -1.55
     actually
    -1.54
     on
    -1.54
     usually
    -1.48
     by
    -1.47
     all
    -1.45
     most
    -1.45
    POSITIVE LOGITS
    <strong>
    2.05
    <b>
    1.79
     zoude
    1.73
     engels
    1.66
     kalender
    1.61
     pittores
    1.50
    genodigd
    1.49
     pengar
    1.48
     wortel
    1.45
     geene
    1.44
    Activations Density 0.008%

    No Known Activations