Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 425
    Prev
    Next
    INDEX
    Explanations

    who or what is affected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ل
    1.88
    ა
    1.20
    ίας
    1.05
    야
    1.05
    
    1.05
    クリ
    1.02
    но
    1.00
    ו
    0.99
    اسی
    0.94
    لل
    0.94
    POSITIVE LOGITS
    ments
    1.64
    s
    1.45
    ment
    1.22
    ren
    1.09
    x
    1.09
    re
    1.08
    et
    1.04
    mente
    0.97
    gt
    0.97
     метра
    0.96
    Activations Density 0.002%

    No Known Activations