© 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. 49561
    Prev
    Next
    INDEX
    Explanations

    regions, countries, and jurisdictions

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

    universities and geographical regions

    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
    🖊
    0.39
     گلوکار
    0.38
    泵
    0.38
    鞦
    0.38
    وْ
    0.38
    Lyrics
    0.38
     חיצוני
    0.37
    钦
    0.37
    颌
    0.37
    詈
    0.36
    POSITIVE LOGITS
     universitet
    0.58
     region
    0.56
     regioni
    0.54
     clans
    0.53
     universidades
    0.52
     universities
    0.52
     subcontinent
    0.52
     regions
    0.52
     প্রদেশ
    0.52
    regions
    0.51
    Activations Density 0.099%

    No Known Activations