© 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. 100641
    Prev
    Next
    INDEX
    Explanations

    Director titles

    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
    and
    -2.86
    ية
    -2.55
    It
    -2.50
    er
    -2.48
    to
    -2.45
    {
    -2.30
    2
    -2.27
    They
    -2.11
    事も
    -2.09
    ation
    -2.06
    POSITIVE LOGITS
    wiście
    2.53
    i
    2.30
     ehemalige
    2.14
     Director
    2.09
    葑
    2.02
    郿
    2.00
    ről
    2.00
     Jahrhunderts
    1.98
     alebo
    1.98
     instalar
    1.98
    Activations Density 0.006%

    No Known Activations