© 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. 120513
    Prev
    Next
    INDEX
    Explanations

    Arabica and United Arab Emirates

    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
    ри
    1.62
    ت
    1.54
    ת
    1.53
    on
    1.45
    ق
    1.44
    خ
    1.43
    ا
    1.41
    ن
    1.37
    תה
    1.35
    ра
    1.34
    POSITIVE LOGITS
    ]
    1.13
     for
    0.96
    อร์
    0.95
    }
    0.91
    Arab
    0.90
    OL
    0.89
     Arab
    0.89
    :
    0.88
    AY
    0.85
    ”
    0.84
    Activations Density 0.001%

    No Known Activations