© 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. 129165
    Prev
    Next
    INDEX
    Explanations

    spring and summer

    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
     is
    -1.49
    ’)
    -1.45
     mostrar
    -1.41
    out
    -1.34
     beschreibt
    -1.33
    詬
    -1.33
    {'
    -1.32
    咴
    -1.31
    偸
    -1.28
    جهزة
    -1.27
    POSITIVE LOGITS
     of
    1.46
    ociação
    1.45
    .''
    1.45
    罢
    1.33
    之时
    1.32
    ."
    1.31
    隸
    1.30
     aquello
    1.29
    вів
    1.28
     it
    1.27
    Activations Density 0.012%

    No Known Activations