© 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-65K
    7. 5674
    Prev
    Next
    INDEX
    Explanations

    chinese and vietnamese contrasting concepts

    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_65k_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
    _
    0.79
    दर्
    0.73
    formerly
    0.72
    ko
    0.71
    Cit
    0.71
    svelte
    0.70
    P
    0.70
     குறிப்பிட்டு
    0.69
    ベ
    0.69
    Sol
    0.68
    POSITIVE LOGITS
     syllabus
    0.86
     cultura
    0.78
     ontology
    0.76
     totalitarian
    0.76
     embracing
    0.75
     embrace
    0.75
     encompasses
    0.74
     suivie
    0.73
     decou
    0.73
     retrieving
    0.73
    Activations Density 0.001%

    No Known Activations