© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2312
    Prev
    Next
    INDEX
    Explanations

    capital of countries and casing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    א
    1.39
    д
    1.34
    ک
    1.34
    ב
    1.27
    ある
    1.26
    ग
    1.26
    یم
    1.25
     νέα
    1.25
    क
    1.23
    いき
    1.22
    POSITIVE LOGITS
    er
    1.33
    in
    1.17
    on
    1.16
    ed
    1.16
    m
    1.16
    och
    1.14
    for
    1.12
    ur
    1.11
     for
    1.10
    om
    1.09
    Activations Density 0.335%

    No Known Activations