© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4306
    Prev
    Next
    INDEX
    Explanations

    Russian, Korean, and Chinese endings

    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
    k
    1.94
    س
    1.84
    ים
    1.67
    a
    1.57
    AM
    1.51
    kách
    1.51
    kannya
    1.50
    kend
    1.48
    kings
    1.48
    an
    1.45
    POSITIVE LOGITS
    тся
    1.51
    있
    1.48
    ️⃣
    1.47
     কিন্ত
    1.38
     случаев
    1.38
     gamme
    1.37
    ⃣
    1.37
     visto
    1.34
    并非
    1.32
    ためには
    1.31
    Activations Density 2.392%

    No Known Activations