© 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. 47777
    Prev
    Next
    INDEX
    Explanations

    Months in dates

    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
    该如何
    -1.91
     zahlreiche
    -1.65
     grabar
    -1.63
    戬
    -1.58
     zobaczyć
    -1.58
    咗
    -1.58
     olduk
    -1.55
     When
    -1.55
     Because
    -1.49
    當時
    -1.49
    POSITIVE LOGITS
     They
    1.74
     baden
    1.72
     geometr
    1.66
    ى
    1.63
    \_
    1.63
     massiv
    1.57
     видит
    1.57
     handels
    1.57
     saa
    1.55
    ;-
    1.55
    Activations Density 0.025%

    No Known Activations