© 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. 16-GEMMASCOPE-2-RES-262K
    7. 90703
    Prev
    Next
    INDEX
    Explanations

    mode decomposition

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Тер
    0.57
    א
    0.54
     ត
    0.52
    К
    0.52
     ಹೆ
    0.50
    ܀
    0.50
    𝙽
    0.50
    ୮
    0.49
    РА
    0.49
     обе
    0.49
    POSITIVE LOGITS
     ferme
    0.46
    는
    0.45
     exploiting
    0.44
     mie
    0.43
     Monk
    0.43
    ાલુ
    0.43
    ohama
    0.43
     camp
    0.42
     Const
    0.42
    вающий
    0.42
    Activations Density 0.000%

    No Known Activations