© 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. 25373
    Prev
    Next
    INDEX
    Explanations

    while it lasts

    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
     telo
    -0.95
     cht
    -0.95
     sewa
    -0.94
     modernen
    -0.92
    就会
    -0.89
     kombi
    -0.87
    athons
    -0.87
     apparten
    -0.87
     osal
    -0.86
    なのですが
    -0.85
    POSITIVE LOGITS
     still
    1.30
     todavía
    1.20
     before
    1.07
    innan
    0.94
     هنوز
    0.93
     ahora
    0.93
     solange
    0.91
     възможно
    0.90
    zköz
    0.88
     antes
    0.88
    Activations Density 0.015%

    No Known Activations