© 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-262K
    7. 6031
    Prev
    Next
    INDEX
    Explanations

    implementations and operational steps

    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
     Еще
    1.54
    ように
    1.45
    즌
    1.36
    ination
    1.34
    féle
    1.34
    וני
    1.33
     Надо
    1.28
    sqlite
    1.27
    accum
    1.27
    ESS
    1.24
    POSITIVE LOGITS
    ли
    2.08
    ف
    1.63
    ри
    1.55
    ти
    1.49
    
    1.44
    ті
    1.41
          
    1.38
    ص
    1.34
        
    1.33
    ੇ
    1.33
    Activations Density 0.046%

    No Known Activations