© 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. 3309
    Prev
    Next
    INDEX
    Explanations

    be able to

    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
    手間
    0.67
    不做
    0.62
     നിങ്ങൾ
    0.61
     hmm
    0.60
     참고
    0.60
     ለ
    0.58
     истины
    0.58
     sakk
    0.58
    InfoHeader
    0.57
    讳
    0.57
    POSITIVE LOGITS
     ability
    4.45
     able
    4.40
     Ability
    3.89
    Ability
    3.75
    能够
    3.57
    能夠
    3.34
     Able
    3.27
     capaz
    3.16
    Able
    3.15
    能
    3.11
    Activations Density 1.222%

    No Known Activations