© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71559
    Prev
    Next
    INDEX
    Explanations

    final parts or counts

    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_22/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
    getStart
    -0.85
     preparatory
    -0.84
    ŭ
    -0.79
     Preparatory
    -0.78
    Introducción
    -0.77
    oriasis
    -0.77
    refront
    -0.77
    牠
    -0.77
     opener
    -0.77
    Ưu
    -0.76
    POSITIVE LOGITS
     rear
    1.14
     ending
    1.14
     finish
    1.10
     backend
    1.02
     finishing
    0.99
    尾
    0.94
     ends
    0.90
    后
    0.89
     Finish
    0.88
    后面的
    0.88
    Activations Density 0.128%

    No Known Activations