© 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. 74889
    Prev
    Next
    INDEX
    Explanations

    containment within defined limits

    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
     DIFFERENT
    -1.62
     participer
    -1.45
    χη
    -1.43
     faciliter
    -1.39
     Propiedad
    -1.39
     présenter
    -1.38
     discuter
    -1.37
     contribuer
    -1.36
     travailler
    -1.35
    jds
    -1.34
    POSITIVE LOGITS
     other
    2.02
     includes
    1.77
     between
    1.73
     had
    1.64
     any
    1.58
     within
    1.50
     for
    1.45
    m
    1.44
    between
    1.42
    ).
    1.41
    Activations Density 0.092%

    No Known Activations