© 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. 128052
    Prev
    Next
    INDEX
    Explanations

    digital content and offers

    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
     other
    -1.32
    blij
    -1.30
     seemingly
    -1.13
     two
    -1.10
     such
    -1.04
    زيز
    -1.02
     seeming
    -1.02
    Filmographie
    -1.00
    払
    -0.99
    kø
    -0.98
    POSITIVE LOGITS
     mejorando
    1.02
    -[
    1.00
     ofreciendo
    0.99
     infancia
    0.99
    ままで
    0.99
    न्त
    0.98
    -(
    0.98
    istered
    0.97
    )">
    0.96
    converse
    0.95
    Activations Density 0.045%

    No Known Activations