© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40587
    Prev
    Next
    INDEX
    Explanations

    copies speech patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     защото
    0.51
     счастли
    0.47
    kont
    0.47
     уют
    0.47
     βρί
    0.46
    Ironically
    0.45
     ука
    0.44
     Ин
    0.44
    젝
    0.44
     因为
    0.43
    POSITIVE LOGITS
    今後の
    0.44
     messages
    0.44
     spokes
    0.42
     styleUrls
    0.41
     discussions
    0.41
    再び
    0.40
     nodded
    0.39
     taches
    0.39
     again
    0.39
     Texte
    0.39
    Activations Density 0.004%

    No Known Activations