© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3596
    Prev
    Next
    INDEX
    Explanations

    small

    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_16k_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
    liği
    1.55
     notably
    1.48
    িয়া
    1.48
     ยก
    1.45
    ่
    1.45
    cular
    1.41
    行く
    1.41
    lly
    1.41
     ਨਾਲ
    1.38
    不见
    1.34
    POSITIVE LOGITS
    小的
    2.05
    pox
    2.02
    一些
    1.60
    
    1.54
    op
    1.51
    ار
    1.51
    하였다
    1.51
    🙉
    1.51
     годах
    1.49
    ">(</
    1.48
    Activations Density 0.203%

    No Known Activations