© 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. 8605
    Prev
    Next
    INDEX
    Explanations

    listing examples within categories

    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
    💟
    1.18
    -
    1.11
    le
    1.10
    ile
    1.10
    i
    1.09
    ’
    1.09
    ol
    1.08
    _
    1.08
    ien
    1.08
    kl
    1.08
    POSITIVE LOGITS
     Yardım
    2.10
     Spreadsheet
    2.09
     Đặc
    2.07
     Bóng
    2.06
     Vật
    2.01
     Firmware
    2.01
     Hydrochloride
    2.00
     Giáo
    1.98
     Đầu
    1.98
     Tập
    1.98
    Activations Density 0.380%

    No Known Activations