© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45398
    Prev
    Next
    INDEX
    Explanations

    political and technical subfields

    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
     gosto
    -1.48
     WHILE
    -1.34
    ?“
    -1.32
     DURING
    -1.28
    当时
    -1.27
    nitř
    -1.25
     terremoto
    -1.24
     eases
    -1.24
    дают
    -1.24
     esos
    -1.24
    POSITIVE LOGITS
     as
    1.91
    ต่างๆ
    1.41
    cheiden
    1.34
     diğer
    1.34
     he
    1.34
     سایر
    1.31
    ToolStripButton
    1.30
     here
    1.30
     الأخرى
    1.28
     gallant
    1.26
    Activations Density 0.102%

    No Known Activations