© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 259025
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zi
    0.49
    Stop
    0.48
    let
    0.48
    2
    0.48
    <h5>
    0.47
    blackjack
    0.47
    Selon
    0.47
    Ext
    0.47
    chemin
    0.46
     puis
    0.46
    POSITIVE LOGITS
     ý
    0.53
     Agriculture
    0.51
     Appellate
    0.50
     Apostle
    0.48
     beheld
    0.47
     GOVERNMENT
    0.46
     வந்தார்
    0.46
     சிறிது
    0.46
     محبت
    0.45
     Agricultural
    0.45
    Activations Density 0.000%

    No Known Activations