© 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. 252146
    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
     Dest
    0.48
    í
    0.46
     Default
    0.44
    atia
    0.43
     Us
    0.43
    ST
    0.43
     After
    0.43
     Pleasure
    0.43
     संतान
    0.43
     External
    0.41
    POSITIVE LOGITS
    א
    0.49
    함
    0.49
    ர்ப
    0.48
    ಸ್ಕ
    0.48
    衝撃
    0.46
    ંગ
    0.46
    関連
    0.46
    गर्
    0.46
    関係
    0.46
     ನ್ಯಾಯ
    0.46
    Activations Density 0.001%

    No Known Activations