© 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. 22-GEMMASCOPE-2-RES-16K
    7. 3396
    Prev
    Next
    INDEX
    Explanations

    class C followed by Text

    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
    Negative Logits
     ……………………
    0.91
    aphosa
    0.91
     gacchati
    0.89
     …………
    0.87
     jumlah
    0.87
     ………………………………..
    0.80
     অভি
    0.80
    𝕜
    0.80
     tatha
    0.79
     거야
    0.79
    POSITIVE LOGITS
    राने
    0.66
    Peter
    0.65
    เวอร์
    0.63
     Ally
    0.63
     Vivi
    0.62
     Pione
    0.62
    現
    0.61
    MVCProject
    0.61
    โรค
    0.61
    合う
    0.61
    Activations Density 0.302%

    No Known Activations