© 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. 31-GEMMASCOPE-2-RES-262K
    7. 37146
    Prev
    Next
    INDEX
    Explanations

    newly explaining what makes

    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_31_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
     люди
    0.42
     ఉంది
    0.40
     квартиры
    0.40
     самый
    0.39
     класи
    0.39
    ️
    0.39
     فرنسا
    0.38
     знамени
    0.38
    ⚠
    0.38
     ऑस्ट्रेलिया
    0.38
    POSITIVE LOGITS
     neue
    0.48
     nowych
    0.44
    新たに
    0.44
     newly
    0.42
     neuen
    0.41
    新たな
    0.40
     resten
    0.39
     consensual
    0.38
     pozosta
    0.38
     henceforth
    0.37
    Activations Density 0.000%

    No Known Activations