© 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. 40-GEMMASCOPE-2-RES-262K
    7. 36526
    Prev
    Next
    INDEX
    Explanations

    South Australia

    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_40_width_262k_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
    NSW
    0.44
     NSW
    0.39
    agona
    0.37
    {%
    0.36
    壢
    0.35
    াবলী
    0.35
     BCR
    0.35
     {%
    0.34
     znan
    0.34
     Hv
    0.34
    POSITIVE LOGITS
     Adelaide
    0.95
     SA
    0.60
     Charleston
    0.60
    elaide
    0.53
     South
    0.53
     Flinders
    0.52
    South
    0.52
     Sioux
    0.52
     Yank
    0.51
     SOUTH
    0.47
    Activations Density 0.003%

    No Known Activations