© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85659
    Prev
    Next
    INDEX
    Explanations

    Late Jurassic, Cretaceous, culture, periods

    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
     jakiś
    -1.59
     usw
    -1.56
     the
    -1.48
    ⤥
    -1.33
     fiind
    -1.32
     feit
    -1.31
    ettu
    -1.31
    を紹介
    -1.27
    oved
    -1.26
    ddd
    -1.26
    POSITIVE LOGITS
     even
    1.47
    роятно
    1.40
    isième
    1.27
    時間は
    1.26
     both
    1.24
     dirigez
    1.24
     حتی
    1.22
     bahkan
    1.21
    גם
    1.21
     of
    1.16
    Activations Density 0.017%

    No Known Activations