© 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. 103888
    Prev
    Next
    INDEX
    Explanations

    denied allegations or claims

    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
     also
    -1.54
     only
    -1.47
     cukup
    -1.39
    外人
    -1.36
     sacerdotes
    -1.32
     accustomed
    -1.31
     semakin
    -1.30
     nails
    -1.30
     cukru
    -1.30
     insightful
    -1.29
    POSITIVE LOGITS
    StringVar
    1.45
     kule
    1.34
    $-$
    1.29
    استفاده
    1.29
    which
    1.28
    錾
    1.27
    but
    1.26
     gani
    1.23
     kula
    1.23
    倻
    1.23
    Activations Density 0.014%

    No Known Activations