© 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. 73769
    Prev
    Next
    INDEX
    Explanations

    number thousand separator

    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
    撂
    -2.19
    岨
    -2.14
     hears
    -2.03
     guides
    -2.03
    揪
    -1.95
    所で
    -1.92
    蘼
    -1.92
    廰
    -1.90
    
    -1.88
     materiaal
    -1.87
    POSITIVE LOGITS
    ком
    2.34
    isation
    2.14
    ным
    2.11
    訁
    2.08
    как
    2.06
     You
    2.02
    ان
    1.98
    ників
    1.95
    chtenstein
    1.93
    izes
    1.91
    Activations Density 0.014%

    No Known Activations