© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 30597
    Prev
    Next
    INDEX
    Explanations

    comida mexicana, Hotel, Meat, multiline

    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
    ur
    1.59
    ag
    1.38
    𝓶
    1.38
    了
    1.33
    І
    1.31
    ної
    1.30
     pores
    1.27
    ladesh
    1.25
     frantically
    1.25
    诒
    1.24
    POSITIVE LOGITS
    та
    1.41
    دا
    1.33
    ா
    1.30
     lingu
    1.25
    op
    1.23
    
    1.20
     behalf
    1.18
     размере
    1.18
     dein
    1.17
     länger
    1.17
    Activations Density 0.001%

    No Known Activations