© 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. 10-GEMMASCOPE-RES-131K
    7. 71515
    Prev
    Next
    INDEX
    Explanations

    difference between things

    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_10/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
     is
    -3.03
     otros
    -1.71
     has
    -1.64
    ;
    -1.63
     where
    -1.56
    ));
    -1.56
     president
    -1.52
     itself
    -1.49
     与
    -1.48
     in
    -1.46
    POSITIVE LOGITS
     olika
    1.79
    次回は
    1.67
     these
    1.62
    gambarkan
    1.62
    そりゃ
    1.60
     použití
    1.60
    以上です
    1.59
     parfü
    1.55
    棪
    1.54
     eivät
    1.53
    Activations Density 0.107%

    No Known Activations