© 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. 16-GEMMASCOPE-2-RES-262K
    7. 110012
    Prev
    Next
    INDEX
    Explanations

    antiretroviral therapy, hair removal, whiskey

    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
    ות
    0.67
     conquests
    0.56
    ק
    0.54
    י
    0.53
    ATION
    0.52
     churches
    0.50
     idols
    0.50
    न
    0.50
    ون
    0.49
     クロ
    0.49
    POSITIVE LOGITS
    সহিত
    0.51
    Serum
    0.50
    )
    0.49
    Sun
    0.48
    çoit
    0.48
    ى
    0.47
    Mos
    0.46
    swire
    0.46
     اضافه
    0.46
    Salle
    0.46
    Activations Density 0.001%

    No Known Activations