© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44754
    Prev
    Next
    INDEX
    Explanations

    URL query parameters like `id=` or `p=`

    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
     but
    -2.11
     '
    -1.75
     of
    -1.61
    ではなく
    -1.59
     
    -1.57
     who
    -1.34
     แต่
    -1.34
    ronesia
    -1.33
     extremely
    -1.32
     didn
    -1.27
    POSITIVE LOGITS
    Appellants
    1.54
     vaksin
    1.52
    Does
    1.46
     októ
    1.44
     OGSÅ
    1.43
    Переваги
    1.42
     pendaftaran
    1.42
     this
    1.41
    Недоліки
    1.41
     Terbaru
    1.40
    Activations Density 0.021%

    No Known Activations