© 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-65K
    7. 8830
    Prev
    Next
    INDEX
    Explanations

    beginning of sequence

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ма
    0.96
    ⾏
    0.96
    ⼀
    0.95
     OBJECTTYPE
    0.92
    ພວກເຮ
    0.91
     довольно
    0.90
     ########.
    0.89
    樀
    0.88
     cenderung
    0.87
    ਫ਼
    0.86
    POSITIVE LOGITS
    less
    0.79
     R
    0.72
     hate
    0.71
     hates
    0.69
     and
    0.68
    涙
    0.66
     없고
    0.65
     L
    0.64
    верх
    0.63
    es
    0.63
    Activations Density 0.182%

    No Known Activations