© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84411
    Prev
    Next
    INDEX
    Explanations

    Sin City Presents magazine

    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
     затем
    -1.57
     ※
    -1.46
    ^^
    -1.46
    鰱
    -1.42
    Karena
    -1.39
     focusing
    -1.33
     「
    -1.32
    ванні
    -1.31
     people
    -1.30
    ᓚ
    -1.30
    POSITIVE LOGITS
     pensive
    1.46
     infatu
    1.46
    Siddhartha
    1.45
    
    1.42
     surpasses
    1.42
    Hulk
    1.41
    越是
    1.41
     itself
    1.41
     Another
    1.40
    可以说是
    1.39
    Activations Density 10.510%

    No Known Activations