© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 142035
    Prev
    Next
    INDEX
    Explanations

    East Asia and country borders

    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_16_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
     
    0.59
    第一个
    0.56
     computeEncoder
    0.55
     the
    0.53
     chunkSize
    0.52
     panic
    0.52
    ช
    0.52
    Lucy
    0.51
    4
    0.51
     były
    0.50
    POSITIVE LOGITS
    मताओं
    0.62
     ಆದ್ದರಿಂದ
    0.61
     मर्दों
    0.61
     typu
    0.60
     அவற்ற
    0.56
     সাম্রাজ
    0.56
    धिकारिक
    0.56
     電力
    0.56
     பார்வைய
    0.55
     TRANSPORTURI
    0.55
    Activations Density 0.061%

    No Known Activations