© 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. 22-GEMMASCOPE-RES-131K
    7. 33053
    Prev
    Next
    INDEX
    Explanations

    percentages and quantities

    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
     arī
    -1.28
    Anche
    -1.27
    bodyParser
    -1.11
    ：……
    -1.09
    rekli
    -1.02
     также
    -1.00
     infierno
    -0.99
     Diese
    -0.96
    xxi
    -0.96
    迭
    -0.96
    POSITIVE LOGITS
     until
    1.17
    )
    1.16
    特に
    1.16
    当時は
    1.15
     for
    1.15
    遑
    1.13
     zelfs
    1.03
     perhaps
    1.02
     mów
    1.02
     at
    1.00
    Activations Density 0.077%

    No Known Activations