© 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. 253040
    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
     Directeur
    0.50
     하나님의
    0.48
     belliger
    0.46
    ůli
    0.45
     drunkenness
    0.43
     lég
    0.43
     የእ
    0.43
     油
    0.43
     zieht
    0.42
     書い
    0.42
    POSITIVE LOGITS
    महल
    0.55
    वेलकम
    0.48
     पार्श्व
    0.46
     Consecutive
    0.46
    𝒅
    0.46
    兟
    0.46
    ધો
    0.45
    nucleus
    0.45
    трон
    0.45
    𝖓
    0.45
    Activations Density 0.008%

    No Known Activations