© 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. 8813
    Prev
    Next
    INDEX
    Explanations

    phrasal constructions often following common topics

    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
     boyunca
    0.83
     Pentru
    0.82
    ሽ
    0.74
    obian
    0.72
     спорттук
    0.72
    গুণ
    0.72
    锂
    0.71
     kültür
    0.71
    에서는
    0.70
     tarafından
    0.70
    POSITIVE LOGITS
     troublesome
    0.67
     συγκεκρι
    0.63
    andfeel
    0.61
     annoying
    0.59
     τοῦ
    0.57
     stipulation
    0.57
     прось
    0.56
     Kauff
    0.56
    갖
    0.56
     stuff
    0.56
    Activations Density 1.230%

    No Known Activations