© 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. 128641
    Prev
    Next
    INDEX
    Explanations

    html special characters 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
     in
    -1.97
     by
    -1.88
     as
    -1.84
     on
    -1.77
     at
    -1.63
     with
    -1.55
     (
    -1.54
     also
    -1.49
     of
    -1.45
     all
    -1.43
    POSITIVE LOGITS
    colgante
    1.59
     miniaturka
    1.55
     görüntüsü
    1.47
     zubehör
    1.46
    klere
    1.46
    ㌘
    1.45
     muñecas
    1.45
     kompati
    1.44
     verschillende
    1.43
    archiwizowane
    1.41
    Activations Density 0.011%

    No Known Activations