© 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. 41026
    Prev
    Next
    INDEX
    Explanations

    Ter-

    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
    C
    -2.13
     เรา
    -2.08
    蟶
    -2.06
    牁
    -2.03
     quatre
    -2.02
    鸸
    -2.00
    ſtra
    -1.99
     内衣
    -1.95
    鏷
    -1.94
     baie
    -1.92
    POSITIVE LOGITS
    乆
    2.23
     boasts
    2.13
    .’’
    2.09
     notices
    2.03
    aptors
    2.02
    there
    2.00
    ,’’
    1.97
    寕
    1.93
     shows
    1.92
     Drittel
    1.92
    Activations Density 0.001%

    No Known Activations