© 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. 20988
    Prev
    Next
    INDEX
    Explanations

    feel free 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
     when
    -2.16
     When
    -2.03
     sizeable
    -2.00
     Because
    -1.89
     بسبب
    -1.87
     solchen
    -1.86
     seemingly
    -1.85
     säga
    -1.83
     Ironically
    -1.81
     unrelenting
    -1.81
    POSITIVE LOGITS
    ’
    2.02
    premier
    1.96
     !!!!
    1.78
     bouteilles
    1.77
    negara
    1.77
     XVII
    1.77
    
    1.75
     الشركة
    1.74
     герои
    1.73
     😊
    1.73
    Activations Density 0.003%

    No Known Activations