© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7481
    Prev
    Next
    INDEX
    Explanations

    usage limits

    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
    间的
    0.85
    ඍ
    0.80
                
    0.78
     outlier
    0.77
     honti
    0.77
     automatis
    0.77
     oblique
    0.75
    ل
    0.75
     vibration
    0.75
     uptime
    0.75
    POSITIVE LOGITS
    ри
    0.82
    isso
    0.79
     barras
    0.77
    hesda
    0.73
     foncé
    0.73
    主义
    0.73
    ot
    0.73
     of
    0.72
    iswa
    0.72
    ok
    0.71
    Activations Density 0.228%

    No Known Activations