© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2689
    Prev
    Next
    INDEX
    Explanations

    say goodbye

    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
    Negative Logits
    😂
    3.07
    ಯೇ
    2.96
    ম
    2.93
    𝗥
    2.90
    கு
    2.81
     اتارنا
    2.78
    م
    2.78
    ॠ
    2.75
     vying
    2.74
     cwd
    2.73
    POSITIVE LOGITS
     goodbye
    2.95
    dust
    2.86
    dete
    2.86
    و
    2.80
    dul
    2.79
    isotropic
    2.78
    ит
    2.74
    eté
    2.73
    elif
    2.72
    evsky
    2.68
    Activations Density 0.212%

    No Known Activations