© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50341
    Prev
    Next
    INDEX
    Explanations

    Russian Offensive, societal stereotypes, historical context

    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_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
    结果
    0.50
     Σ
    0.49
     Sử
    0.48
     Θε
    0.47
    显示
    0.47
     Αγ
    0.46
    激发
    0.46
     Με
    0.45
     调用
    0.45
     Κο
    0.44
    POSITIVE LOGITS
     uchun
    0.51
     anto
    0.50
     ಅಥವಾ
    0.47
    chats
    0.46
     otor
    0.46
    iriman
    0.45
    lach
    0.45
    contrar
    0.45
    TOR
    0.44
    真心
    0.44
    Activations Density 0.008%

    No Known Activations