© 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. 84266
    Prev
    Next
    INDEX
    Explanations

    fair use and copyright law

    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
    ilización
    -1.57
    lamiento
    -1.56
     liées
    -1.48
    
    -1.45
     (?)
    -1.44
    ⁵
    -1.41
    茕
    -1.41
    (?)
    -1.38
     två
    -1.37
     %\
    -1.35
    POSITIVE LOGITS
     which
    2.06
     troubles
    1.48
     regarding
    1.47
     any
    1.45
     then
    1.38
     needing
    1.37
     predomin
    1.34
     their
    1.34
     only
    1.32
     at
    1.31
    Activations Density 0.077%

    No Known Activations