© 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. 254330
    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
     Eğer
    0.60
     дія
    0.55
     ಡ
    0.54
     IncludeField
    0.53
    ವಿಲ್ಲ
    0.53
     ಯಾವುದೇ
    0.50
    お願い致します
    0.50
     дії
    0.49
    കള്‍
    0.48
     মিনি
    0.48
    POSITIVE LOGITS
    v
    0.49
     cons
    0.49
     m
    0.48
     brought
    0.47
     rangement
    0.46
    ab
    0.45
     statistics
    0.45
    Mex
    0.44
     surface
    0.44
     coin
    0.44
    Activations Density 0.001%

    No Known Activations