© 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. 58537
    Prev
    Next
    INDEX
    Explanations

    born to

    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
     queridos
    -1.88
     efectivos
    -1.85
     atractivos
    -1.80
    
    -1.70
     oryginal
    -1.70
     craindre
    -1.70
    蛱
    -1.69
     standaard
    -1.67
    isieren
    -1.67
     continúas
    -1.65
    POSITIVE LOGITS
     They
    2.30
    However
    2.05
    2
    1.98
    s
    1.92
    This
    1.90
    with
    1.89
    5
    1.79
    A
    1.77
    While
    1.74
     их
    1.73
    Activations Density 0.011%

    No Known Activations