© 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. 1173
    Prev
    Next
    INDEX
    Explanations

    law of thermodynamics

    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
    
    1.25
    ipedi
    1.21
     purpose
    1.14
    
    1.13
     throughput
    1.12
     drawable
    1.10
    ের
    1.10
     removing
    1.10
     republished
    1.10
     campus
    1.07
    POSITIVE LOGITS
     $(<
    1.15
    وْ
    1.11
    其实
    1.09
     совершенно
    1.08
     Độ
    1.08
    டைய
    1.07
     температур
    1.06
     namelijk
    1.05
    並沒有
    1.05
     genieten
    1.05
    Activations Density 0.002%

    No Known Activations