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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 3888
    Prev
    Next
    INDEX
    Explanations

    protests and 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_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
     physiologique
    0.61
     ያስፈል
    0.60
    韩
    0.60
    泽
    0.58
     হ্যান
    0.57
     পৃথিব
    0.57
     دنیا
    0.56
     باسکٹ
    0.56
     చక్కెర
    0.56
    润
    0.56
    POSITIVE LOGITS
     paramilitary
    1.12
     militia
    1.10
     militias
    1.09
     militants
    1.05
     insurgents
    1.04
     insurgency
    1.03
     insurg
    1.02
     violence
    0.99
     skirm
    0.99
     uprisings
    0.98
    Activations Density 0.104%

    No Known Activations