© 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. 116297
    Prev
    Next
    INDEX
    Explanations

    close your eyes

    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
    س
    0.61
     polynomials
    0.52
     annexed
    0.51
     secondes
    0.50
     arquivos
    0.49
     polinom
    0.49
     einfacher
    0.49
     organisiert
    0.49
    Alpes
    0.48
     algebraic
    0.48
    POSITIVE LOGITS
     an
    0.50
     a
    0.50
     जताई
    0.47
    绶
    0.46
     Magento
    0.46
    價值
    0.45
     Thunderbird
    0.45
    ing
    0.44
     രംഗ
    0.44
     संपन्न
    0.43
    Activations Density 0.001%

    No Known Activations