© 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. 103110
    Prev
    Next
    INDEX
    Explanations

    beginning of phrases or code

    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
     düğün
    -0.97
     we
    -0.90
    駐車
    -0.88
     våra
    -0.86
    FFS
    -0.83
     зданий
    -0.82
    逃跑
    -0.81
     små
    -0.81
     σύ
    -0.80
    噩
    -0.80
    POSITIVE LOGITS
     Perhaps
    1.09
    Perhaps
    1.03
     everything
    0.98
    åringen
    0.97
    ឈ
    0.97
    所有
    0.92
    ---|---|
    0.91
     perhaps
    0.90
    Everything
    0.90
     menggunakan
    0.90
    Activations Density 0.006%

    No Known Activations