© 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. 14814
    Prev
    Next
    INDEX
    Explanations

    but not limited to

    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
     unhealthy
    1.05
    yielding
    1.02
    絫
    0.94
     interiores
    0.89
     turbulent
    0.88
     unhappy
    0.87
    
    0.87
     surges
    0.86
     strugg
    0.86
     towels
    0.85
    POSITIVE LOGITS
     शामिल
    1.07
    これ
    1.05
    Included
    1.04
     포함
    1.04
    鳅
    1.03
    cheon
    1.01
     참석
    1.00
    vrd
    1.00
    菜单
    1.00
     вероятность
    0.99
    Activations Density 0.019%

    No Known Activations