© 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. 12018
    Prev
    Next
    INDEX
    Explanations

    employment-based immigration categories

    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
    throp
    0.44
    whal
    0.43
    伊
    0.42
    userId
    0.39
    voje
    0.38
    ГО
    0.37
    Yah
    0.37
    kker
    0.36
    صة
    0.35
    auh
    0.35
    POSITIVE LOGITS
     Genealogy
    0.40
     Previous
    0.39
     ]:
    0.38
     می‌توان
    0.38
     Broughton
    0.36
    फर
    0.36
     :\
    0.36
     )।
    0.36
    ᠩ
    0.36
    ovať
    0.36
    Activations Density 0.001%

    No Known Activations