© 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. 69226
    Prev
    Next
    INDEX
    Explanations

    Q: followed by colon

    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
    -
    -2.67
    可在
    -1.98
    $
    -1.95
    おわりに
    -1.92
     folgenden
    -1.91
    CurtirCurtir
    -1.88
     substandard
    -1.88
    la
    -1.85
     он
    -1.84
    ープン
    -1.84
    POSITIVE LOGITS
    轳
    2.50
    ⎘
    2.31
    咈
    2.31
    သ
    2.28
     albeit
    2.19
     apesar
    2.14
    帏
    2.13
    歘
    2.11
     infeliz
    2.06
    躥
    2.06
    Activations Density 0.000%

    No Known Activations