© 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-16K
    7. 10752
    Prev
    Next
    INDEX
    Explanations

    Greek and Spanish word parts

    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_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
    λί
    0.94
    ДУ
    0.91
    reflected
    0.90
    անում
    0.88
    ί
    0.87
    fö
    0.87
     trường
    0.86
     উপস্থিত
    0.86
    ́
    0.85
    ád
    0.85
    POSITIVE LOGITS
    ους
    0.89
    teis
    0.84
    πος
    0.79
    τος
    0.76
    ชั่น
    0.74
    semos
    0.71
    ๋ว
    0.70
    ιος
    0.69
    υν
    0.68
    ες
    0.68
    Activations Density 0.045%

    No Known Activations