© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90891
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Two
    -1.98
    One
    -1.77
     sehr
    -1.76
    Before
    -1.73
     by
    -1.73
     große
    -1.70
    ",
    -1.70
    訶
    -1.67
    Since
    -1.66
    Three
    -1.66
    POSITIVE LOGITS
    乆
    1.67
     semblent
    1.63
    の状態
    1.57
    cestry
    1.54
     但是
    1.54
     are
    1.53
     myriad
    1.51
     they
    1.50
     realizó
    1.49
     agregó
    1.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.