© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5339
    Prev
    Next
    INDEX
    Explanations

    Russian aggression in Ukraine

    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_31_width_16k_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
     бактери
    0.45
    细菌
    0.44
    Delta
    0.43
    ໍ່
    0.43
    Curves
    0.43
    Bac
    0.42
    illae
    0.42
    🕴
    0.41
    验证
    0.41
    Francisco
    0.41
    POSITIVE LOGITS
     Ukraine
    1.20
     यूक्रेन
    1.17
     Ukraj
    1.14
     Ukrainian
    1.13
     Oekra
    1.12
     Ukrain
    1.09
     Ukrainians
    1.09
     Zelensky
    1.06
     Putin
    1.05
     Kyiv
    1.03
    Activations Density 0.128%

    No Known Activations