© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 210528
    Prev
    Next
    INDEX
    Explanations

    graphics brushes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
    ុស
    0.42
     কেঁ
    0.38
     Text
    0.38
     textile
    0.38
    面包
    0.38
     Texte
    0.38
     მდ
    0.38
    鮎
    0.38
     biom
    0.36
     විට
    0.36
    POSITIVE LOGITS
     brushes
    0.44
     paintbrush
    0.39
    ائ
    0.38
    Brush
    0.38
     chuck
    0.38
     sweep
    0.37
     null
    0.36
     brushed
    0.36
    brushes
    0.35
     brush
    0.35
    Activations Density 0.002%

    No Known Activations