© 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. 17-GEMMASCOPE-2-RES-16K
    7. 10426
    Prev
    Next
    INDEX
    Explanations

    or opposing conditions

    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_17_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
    動
    0.72
     práct
    0.70
    තුව
    0.70
    是要
    0.70
     troubling
    0.67
     കൂടുതൽ
    0.67
     commercial
    0.66
     թ
    0.66
    णिज्य
    0.66
     أق
    0.64
    POSITIVE LOGITS
    Similarly
    1.12
    reverse
    1.10
     likewise
    1.07
     reverse
    1.04
     একইভাবে
    1.03
     conversely
    1.02
    Reverse
    1.02
     Similarly
    1.01
     opposit
    1.00
     similarly
    1.00
    Activations Density 0.401%

    No Known Activations