© 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. 13351
    Prev
    Next
    INDEX
    Explanations

    global:: or clr-namespace:

    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
    
    -1.48
    蛲
    -1.45
     Präsidenten
    -1.45
     tradição
    -1.36
    を選択します
    -1.35
    teto
    -1.34
     hóspedes
    -1.32
     Öffentlich
    -1.31
     damaligen
    -1.28
    ৢ
    -1.28
    POSITIVE LOGITS
    when
    1.41
     nü
    1.33
    Neither
    1.33
    Interestingly
    1.32
     four
    1.30
    셴
    1.30
    Because
    1.29
    Зміст
    1.27
    Ці
    1.27
    </em>
    1.27
    Activations Density 0.006%

    No Known Activations