© 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. 119936
    Prev
    Next
    INDEX
    Explanations

    introduces a list

    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
    だらけ
    -1.50
     it
    -1.42
    なども
    -1.40
     
    -1.38
     странице
    -1.38
    ↵↵
    -1.34
     moest
    -1.34
    وروبا
    -1.31
     черные
    -1.30
     haremos
    -1.30
    POSITIVE LOGITS
    :
    2.05
     istimewa
    1.77
    .”
    1.73
    酲
    1.73
    ୈ
    1.71
    淠
    1.69
     vänner
    1.67
    никах
    1.63
    إذا
    1.62
     venerdì
    1.61
    Activations Density 0.088%

    No Known Activations