© 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. 41-GEMMASCOPE-2-RES-262K
    7. 99757
    Prev
    Next
    INDEX
    Explanations

    Spanish place names and descriptors

    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_all/layer_41_width_262k_l0_big
    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
     территория
    0.56
     সড়কে
    0.55
     územ
    0.54
     territo
    0.53
     Protección
    0.52
    ክል
    0.51
    摶
    0.51
    ಧಾರವಾಡ
    0.50
    蕖
    0.50
    海南
    0.50
    POSITIVE LOGITS
     monkeys
    0.44
     three
    0.44
     Dragon
    0.43
     Devil
    0.42
     Queen
    0.42
     Horse
    0.41
     Bishop
    0.41
     Cross
    0.41
     dragon
    0.41
     donkey
    0.41
    Activations Density 0.001%

    No Known Activations