© 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. 120971
    Prev
    Next
    INDEX
    Explanations

    trophoblast and expenses

    np_acts-logits-general · gemini-2.5-flash-lite

    racial characteristics and exploitation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     efforts
    0.46
     foregoing
    0.45
     disparity
    0.45
     decisions
    0.45
     sfor
    0.45
     withstand
    0.44
     '';
    0.43
    esque
    0.43
     scoff
    0.43
     balancing
    0.41
    POSITIVE LOGITS
    ním
    0.57
    ى
    0.54
    وي
    0.50
    घटना
    0.50
    흄
    0.49
    પ
    0.49
    ﻦ
    0.48
     தினம்
    0.48
    чним
    0.47
    ಧಾರವಾಡ
    0.47
    Activations Density 0.000%

    No Known Activations