© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11639
    Prev
    Next
    INDEX
    Explanations

    anterior/posterior directions

    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
     navide
    -1.63
     ekolog
    -1.52
    *
    -1.47
    ات
    -1.45
     especta
    -1.45
     Controle
    -1.43
     atualmente
    -1.40
     fashionable
    -1.40
     instruk
    -1.37
    ishment
    -1.34
    POSITIVE LOGITS
    ;
    1.72
     mentre
    1.52
    。”
    1.51
    b
    1.50
     of
    1.46
    most
    1.45
    begin
    1.42
    fficients
    1.41
    nologue
    1.41
    。」
    1.40
    Activations Density 0.086%

    No Known Activations