© 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. 72670
    Prev
    Next
    INDEX
    Explanations

    asking questions or causes confusion

    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
     sirop
    -1.01
     TÉ
    -0.97
     aldrig
    -0.95
     gré
    -0.95
    棪
    -0.94
     trimestre
    -0.93
    яна
    -0.93
    ІІ
    -0.92
     never
    -0.91
     faciliter
    -0.91
    POSITIVE LOGITS
     deixando
    1.11
     inmediatamente
    1.08
     poignant
    1.05
    optString
    1.02
    了一個
    0.99
     any
    0.98
     When
    0.98
     вспомина
    0.97
     How
    0.95
    豉
    0.95
    Activations Density 0.053%

    No Known Activations