© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106740
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     możemy
    -1.06
     opravdu
    -1.05
     rencontré
    -1.03
     еще
    -1.00
     Whilst
    -0.99
     Amongst
    -0.96
    astify
    -0.96
     mewakili
    -0.95
     anyways
    -0.93
    ների
    -0.92
    POSITIVE LOGITS
     would
    0.86
    держка
    0.84
     ``
    0.84
     deshalb
    0.83
     Cartridge
    0.81
    ``
    0.80
    ⓨ
    0.79
     THING
    0.78
     aceit
    0.78
     esquer
    0.77
    Activations Density 0.004%

    No Known Activations