© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92770
    Prev
    Next
    INDEX
    Explanations

    aggression & violence

    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_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
     člove
    0.55
     człowieka
    0.53
     اعمل
    0.51
     사람은
    0.51
    鐪
    0.50
     człowie
    0.49
     położ
    0.49
     raczej
    0.49
    ඵ
    0.49
    ຂໍ້ມ
    0.49
    POSITIVE LOGITS
    以外
    0.40
     dared
    0.40
    票房
    0.40
     daring
    0.39
    a
    0.38
    岸
    0.38
    菅
    0.38
     aggress
    0.38
    agana
    0.37
     frantic
    0.37
    Activations Density 0.006%

    No Known Activations