© 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. 3639
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
    ر
    2.34
    ний
    2.22
    찜
    2.16
    不過
    1.94
     depan
    1.92
    llan
    1.90
    
    1.88
    ah
    1.86
     savor
    1.85
     μην
    1.84
    POSITIVE LOGITS
    ت
    2.83
    ED
    2.28
    т
    2.19
    ्य
    2.13
    ى
    2.11
    ARE
    2.09
    น้อง
    2.09
    ो
    2.08
    illation
    2.06
    ানের
    2.03
    Activations Density 0.315%

    No Known Activations