© 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. 129294
    Prev
    Next
    INDEX
    Explanations

    introductions to topics

    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
     fourn
    -1.10
     vapeur
    -1.07
    bidities
    -1.06
     ché
    -1.03
    ługość
    -1.03
    %，
    -1.02
    ään
    -1.02
    🎲
    -1.01
     appara
    -1.00
    atste
    -0.99
    POSITIVE LOGITS
     then
    1.24
     to
    1.10
     the
    1.05
     there
    1.02
     thereafter
    1.00
     benö
    0.93
     either
    0.91
     similarly
    0.90
     determinadas
    0.89
     zbyt
    0.89
    Activations Density 0.000%

    No Known Activations