© 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. 59727
    Prev
    Next
    INDEX
    Explanations

    code keywords and types

    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
     deras
    -1.62
     injust
    -1.58
     officier
    -1.49
     gars
    -1.43
     cadeau
    -1.41
     THAN
    -1.41
    inerary
    -1.41
     ,'
    -1.39
     camiset
    -1.38
     DIFFERENT
    -1.37
    POSITIVE LOGITS
     before
    1.74
     time
    1.64
     other
    1.63
     both
    1.54
     makes
    1.46
     make
    1.45
     used
    1.45
     at
    1.45
     should
    1.45
     made
    1.45
    Activations Density 0.057%

    No Known Activations