© 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. 10-GEMMASCOPE-RES-131K
    7. 20667
    Prev
    Next
    INDEX
    Explanations

    Brussels commune, Airlines, sprouts

    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
     עם
    -3.14
    
    -3.06
     první
    -2.86
    ⣜
    -2.77
     avec
    -2.72
     escalate
    -2.52
    蹓
    -2.48
    袿
    -2.48
     skolen
    -2.47
    🧌
    -2.47
    POSITIVE LOGITS
     —
    2.70
    .
    2.67
    ;
    2.61
    0
    2.59
    >
    2.47
    E
    2.38
     inherently
    2.30
    F
    2.25
    ————————————
    2.25
     характеристи
    2.25
    Activations Density 0.002%

    No Known Activations