© 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. 124034
    Prev
    Next
    INDEX
    Explanations

    petroleum, tumblr, names

    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
    "
    -3.98
     
    -3.03
    1
    -2.98
     We
    -2.92
    V
    -2.91
     VERY
    -2.86
     is
    -2.70
     notre
    -2.53
     NEW
    -2.47
     le
    -2.45
    POSITIVE LOGITS
    ل
    2.70
     彼女
    2.69
     商店
    2.67
     婚礼
    2.48
     雑貨
    2.42
    瓩
    2.39
     unparalleled
    2.38
     považ
    2.31
     予約
    2.31
     thirteen
    2.31
    Activations Density 0.011%

    No Known Activations