© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70371
    Prev
    Next
    INDEX
    Explanations

    without

    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
    ers
    -2.13
     vẫn
    -1.78
     MUCH
    -1.77
     ANOTHER
    -1.76
     genug
    -1.76
     STILL
    -1.75
     одному
    -1.74
    需要
    -1.73
     The
    -1.73
     NOW
    -1.65
    POSITIVE LOGITS
    倅
    1.76
    閙
    1.67
     SANTOS
    1.61
    取って
    1.59
     aucun
    1.59
     вышла
    1.56
    焢
    1.54
    landır
    1.52
    tų
    1.52
     fashioned
    1.52
    Activations Density 0.025%

    No Known Activations