© 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. 257412
    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
    ל
    0.61
    л
    0.59
    ה
    0.52
    isch
    0.50
    ischen
    0.50
    ảng
    0.48
    ᴴ
    0.48
    ле
    0.47
    Ми
    0.45
    н
    0.45
    POSITIVE LOGITS
    誂
    0.55
     embryo
    0.53
     cream
    0.51
     pesticide
    0.51
     بدر
    0.50
     dugo
    0.48
     bună
    0.48
     barat
    0.46
     pilot
    0.46
     biaya
    0.46
    Activations Density 0.000%

    No Known Activations