© 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. 33625
    Prev
    Next
    INDEX
    Explanations

    comparisons and assignments

    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
     payé
    -1.69
     délais
    -1.60
     clô
    -1.59
     rafraî
    -1.52
     véhic
    -1.49
     choisis
    -1.49
     rembour
    -1.48
     refroid
    -1.46
     imprimer
    -1.45
     réinitial
    -1.44
    POSITIVE LOGITS
     as
    2.05
     is
    2.03
     was
    1.76
     not
    1.70
     in
    1.62
     or
    1.55
     are
    1.47
     also
    1.45
     just
    1.41
     can
    1.38
    Activations Density 0.003%

    No Known Activations