© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84134
    Prev
    Next
    INDEX
    Explanations

    doing anything

    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
     these
    -0.99
     this
    -0.98
    ⒌
    -0.95
     ию
    -0.95
     této
    -0.94
    parametri
    -0.93
     подоб
    -0.93
    veston
    -0.92
     案内
    -0.91
     этой
    -0.90
    POSITIVE LOGITS
     andare
    1.00
    ınt
    0.85
     otot
    0.84
     tanda
    0.84
    r
    0.83
     PowerPoint
    0.83
     manifiesta
    0.83
    .‏
    0.83
     учре
    0.81
    eBook
    0.81
    Activations Density 0.042%

    No Known Activations