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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1592
    Prev
    Next
    INDEX
    Explanations

    old or older adults

    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_9_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
    当时
    2.78
    គ្នា
    2.75
    ત
    2.70
    cter
    2.65
    níka
    2.63
     arsenic
    2.63
    ০০০
    2.62
    }\{
    2.54
    gé
    2.52
    
    2.51
    POSITIVE LOGITS
    べき
    3.00
    fashioned
    2.96
    жно
    2.86
     fashioned
    2.56
    ת
    2.56
    marshal
    2.55
    挝
    2.52
    k
    2.52
    ग
    2.40
     वर्ग
    2.39
    Activations Density 0.148%

    No Known Activations