© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6903
    Prev
    Next
    INDEX
    Explanations

    pleasure meeting you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    Negative Logits
    夫
    0.78
     frère
    0.65
     friv
    0.64
     hermano
    0.64
    ড়ে
    0.64
     theme
    0.64
     brethren
    0.64
     sugiere
    0.61
     sugger
    0.61
    退
    0.60
    POSITIVE LOGITS
    Meet
    1.33
     meets
    1.33
     meeting
    1.32
     met
    1.31
     Meet
    1.29
     meet
    1.27
    meet
    1.27
    meeting
    1.25
     bertemu
    1.22
     Meeting
    1.19
    Activations Density 0.294%

    No Known Activations