© 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. 61311
    Prev
    Next
    INDEX
    Explanations

    reporting observations

    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
     anstatt
    -1.69
     harap
    -1.64
    but
    -1.62
     épisode
    -1.62
     ۷
    -1.59
    魠
    -1.57
    ckeye
    -1.50
    mid
    -1.50
    鲮
    -1.49
    ivores
    -1.48
    POSITIVE LOGITS
     when
    1.55
     resistir
    1.48
    óculos
    1.40
    佘
    1.39
     unexpectedly
    1.38
     in
    1.36
     Caused
    1.34
    Betyg
    1.34
     række
    1.33
     impressive
    1.30
    Activations Density 0.030%

    No Known Activations