© 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. 5279
    Prev
    Next
    INDEX
    Explanations

    intricate decorative carvings

    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
     tránsito
    0.79
     ресурсов
    0.74
     inertia
    0.74
     पदार्
    0.73
     hậu
    0.71
    readystate
    0.70
    彈
    0.70
    衝撃
    0.68
     rebounded
    0.68
     overpowered
    0.67
    POSITIVE LOGITS
     patterns
    2.12
    图案
    1.90
     Patterns
    1.87
     decoration
    1.87
     carvings
    1.86
     pattern
    1.84
     decorations
    1.83
    patterns
    1.72
     decorating
    1.71
     decorate
    1.69
    Activations Density 0.127%

    No Known Activations