© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34829
    Prev
    Next
    INDEX
    Explanations

    opposition or negation

    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
     ersetzen
    -0.82
    なんとか
    -0.78
     inesperado
    -0.73
     bigotry
    -0.73
     shaming
    -0.71
     harass
    -0.71
     acoso
    -0.70
    自体は
    -0.69
     allude
    -0.69
     intérieure
    -0.68
    POSITIVE LOGITS
    nappropriate
    0.84
    راهيم
    0.84
     prima
    0.82
    gota
    0.82
     multic
    0.81
     espect
    0.80
     seconda
    0.80
    essen
    0.78
    ambigu
    0.78
     cigarette
    0.78
    Activations Density 0.045%

    No Known Activations