© 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. 129268
    Prev
    Next
    INDEX
    Explanations

    tennis court surfaces and foreign words

    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
     this
    -1.63
     when
    -1.55
     in
    -1.39
     if
    -1.38
     of
    -1.37
     that
    -1.33
     all
    -1.33
     have
    -1.31
     just
    -1.30
     because
    -1.23
    POSITIVE LOGITS
     diferite
    1.41
     Dinas
    1.41
    Descriere
    1.40
     utiliser
    1.39
     indiquer
    1.38
     olika
    1.32
     fiabilidad
    1.29
    Katalog
    1.24
    惴
    1.23
     다른
    1.22
    Activations Density 0.002%

    No Known Activations