© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14921
    Prev
    Next
    INDEX
    Explanations

    model answering riddles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    ceding
    0.81
    
    0.79
    meier
    0.74
     incorporación
    0.74
     lesión
    0.73
    করিয়
    0.73
    ⎣
    0.72
    ക്കുകയും
    0.71
    ᱜ
    0.69
    једина
    0.69
    POSITIVE LOGITS
    这是一个
    0.93
     jokes
    0.80
     这
    0.78
     هذا
    0.78
     this
    0.78
    ૂત
    0.75
     This
    0.75
     เหล
    0.74
     these
    0.74
     THIS
    0.74
    Activations Density 0.050%

    No Known Activations