© 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. 258981
    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
     RESPON
    0.50
     yú
    0.49
     pulgadas
    0.48
    égio
    0.48
    晦
    0.47
    有个
    0.46
    сера
    0.46
     власть
    0.46
    ски
    0.46
    leven
    0.46
    POSITIVE LOGITS
     نگر
    0.48
     N
    0.46
     akt
    0.46
    iden
    0.46
     classifying
    0.46
     evid
    0.45
     install
    0.45
     kass
    0.43
    ;
    0.43
     spills
    0.42
    Activations Density 0.001%

    No Known Activations