© 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. 67945
    Prev
    Next
    INDEX
    Explanations

    bask amid sun

    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
    憮
    -2.05
     ก็
    -2.00
     หรือ
    -2.00
    la
    -1.98
     Begleitung
    -1.93
    嚶
    -1.87
    le
    -1.84
    奬
    -1.84
    躥
    -1.82
    軔
    -1.82
    POSITIVE LOGITS
    ("
    1.82
     the
    1.63
     детьми
    1.61
    --
    1.61
    Aceite
    1.60
    全都
    1.52
    Ubic
    1.51
    ,
    1.50
    叫做
    1.50
    forcement
    1.50
    Activations Density 0.006%

    No Known Activations