© 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. 13050
    Prev
    Next
    INDEX
    Explanations

    suit your needs

    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
    ים
    -1.34
     dalších
    -1.33
    ulario
    -1.31
    颂
    -1.30
    』（
    -1.27
    綻
    -1.27
    ulateur
    -1.26
    embroidered
    -1.25
     
    -1.24
    上がり
    -1.24
    POSITIVE LOGITS
     the
    2.38
     Our
    1.73
     They
    1.68
     These
    1.66
     Their
    1.57
     However
    1.56
     Additionally
    1.55
     diinginkan
    1.54
    Our
    1.50
     Some
    1.48
    Activations Density 0.009%

    No Known Activations