© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 5263
    Prev
    Next
    INDEX
    Explanations

    controversial or stirring reactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     فراہم
    0.69
    페
    0.67
     рее
    0.66
     substrate
    0.66
    дя
    0.64
    substrate
    0.64
    ন্ড
    0.64
    ју
    0.63
     Sieg
    0.62
    정
    0.61
    POSITIVE LOGITS
     sparking
    1.96
    引起
    1.95
    引发
    1.93
     sparks
    1.91
     spark
    1.90
     controversial
    1.87
     suscit
    1.77
     elic
    1.75
     stirs
    1.75
     elicit
    1.74
    Activations Density 0.381%

    No Known Activations