© 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. 69829
    Prev
    Next
    INDEX
    Explanations

    more than three

    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
     jį
    -1.64
    ljeno
    -1.60
     itſelf
    -1.59
     eksemp
    -1.56
     entire
    -1.48
    laubnis
    -1.46
     kitab
    -1.41
     both
    -1.41
     imidlertid
    -1.41
     短发
    -1.40
    POSITIVE LOGITS
    first
    1.47
     y
    1.40
     sofern
    1.35
     there
    1.32
     الذي
    1.27
    ,...
    1.27
     Pastikan
    1.27
     用户
    1.22
    zeiti
    1.22
    那种
    1.20
    Activations Density 0.036%

    No Known Activations