© 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. 8727
    Prev
    Next
    INDEX
    Explanations

    Arabic and Hebrew text prefixes

    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
    ो
    1.27
     করিতাম
    1.16
    रिडोर
    1.09
     Cheesecake
    1.05
    ্রো
    1.03
     uczni
    1.00
    EA
    1.00
    )&=
    0.99
    CString
    0.98
    الی
    0.98
    POSITIVE LOGITS
    ي
    1.90
    اً
    1.59
    ون
    1.54
    ري
    1.54
    ية
    1.48
    ले
    1.45
    اي
    1.43
    ли
    1.39
    ні
    1.38
    يه
    1.38
    Activations Density 0.001%

    No Known Activations