© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 235684
    Prev
    Next
    INDEX
    Explanations

    geographic regions and specific items

    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
    Negative Logits
     Сури
    0.47
     στους
    0.46
     সূত্র
    0.45
     emol
    0.45
     inconvén
    0.43
     auc
    0.43
     múltipl
    0.42
     clerks
    0.41
     múlti
    0.41
    尭
    0.41
    POSITIVE LOGITS
    Khi
    0.47
    HIV
    0.46
    persona
    0.46
    Hod
    0.46
    리
    0.46
     上
    0.45
    personas
    0.44
    RA
    0.43
    Thailand
    0.43
    沙漠
    0.43
    Activations Density 0.000%

    No Known Activations