© 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. 10-GEMMASCOPE-RES-131K
    7. 123501
    Prev
    Next
    INDEX
    Explanations

    let me know

    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
    上記
    -2.06
    もちろん
    -2.02
    迓
    -1.82
    ーーーー
    -1.79
     geringen
    -1.78
    錼
    -1.76
    вают
    -1.74
     misconception
    -1.73
     produits
    -1.69
     verbessert
    -1.65
    POSITIVE LOGITS
     in
    2.02
     if
    1.97
    久了
    1.93
     during
    1.92
     of
    1.81
    ՚
    1.73
     after
    1.71
    k
    1.70
    しゃれ
    1.66
     since
    1.63
    Activations Density 0.005%

    No Known Activations