© 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. 85601
    Prev
    Next
    INDEX
    Explanations

    sections, folds, generation, deletion

    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
    at
    -1.70
     خواهند
    -1.65
    ons
    -1.65
    
    -1.64
    癭
    -1.63
    k
    -1.62
    ”;
    -1.62
    咈
    -1.61
    most
    -1.59
     necesidad
    -1.57
    POSITIVE LOGITS
    '
    2.05
    yym
    1.80
    後記
    1.58
    </i>
    1.56
    ,
    1.55
     red
    1.54
    ～～
    1.52
    epochs
    1.48
    ༐
    1.48
    ripsi
    1.45
    Activations Density 0.001%

    No Known Activations