© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13644
    Prev
    Next
    INDEX
    Explanations

    words starting with un

    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
     penjara
    -2.28
    犼
    -2.23
     pelaksanaan
    -2.17
    mpagne
    -2.11
     Bereichen
    -2.09
     hukuman
    -2.08
     penerima
    -2.08
    ugeot
    -2.06
     empezaron
    -2.00
     perjalanan
    -1.98
    POSITIVE LOGITS
    1
    2.83
    2
    2.78
    8
    2.52
    IN
    2.28
    He
    2.27
    m
    2.25
    "
    2.20
    却又
    2.17
    随即
    2.16
     help
    2.13
    Activations Density 0.002%

    No Known Activations