© 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. 34-GEMMASCOPE-RES-131K
    7. 12248
    Prev
    Next
    INDEX
    Explanations

    argued for appellant

    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_34/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
    KJV
    -0.93
    ~•
    -0.88
    ことから
    -0.84
     нарушения
    -0.84
    /¯
    -0.84
    uncio
    -0.82
    ुनिया
    -0.82
    Pastor
    -0.82
     ACTIVITIES
    -0.80
    нял
    -0.80
    POSITIVE LOGITS
     Griechenland
    1.05
     appearing
    1.04
     argued
    0.96
    viewpager
    0.92
    事务
    0.88
     arguing
    0.88
    寐
    0.87
     for
    0.85
    ｭ
    0.85
    вање
    0.84
    Activations Density 0.635%

    No Known Activations