© 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. 226973
    Prev
    Next
    INDEX
    Explanations

    geographic entities and their context

    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
    barn
    0.53
    ems
    0.51
    fil
    0.48
    tos
    0.47
    ős
    0.47
     चिप
    0.47
    <unused2105>
    0.47
     kring
    0.47
     Kräfte
    0.47
     lokale
    0.46
    POSITIVE LOGITS
     ə
    0.50
    Ə
    0.48
    ካት
    0.43
    ৩৯
    0.42
     nə
    0.42
     mnemonic
    0.41
     deliberately
    0.41
    ه‌های
    0.40
     religious
    0.40
     discipline
    0.39
    Activations Density 0.001%

    No Known Activations