© 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-65K
    7. 44670
    Prev
    Next
    INDEX
    Explanations

    spontaneous, often, historic, package

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Our
    0.46
     milling
    0.46
    د
    0.45
    全年
    0.44
    ب
    0.43
     Zacks
    0.43
    名の
    0.42
    ુર
    0.42
    蹟
    0.42
     floods
    0.41
    POSITIVE LOGITS
     nach
    0.48
     બાદ
    0.47
     encabez
    0.46
     coração
    0.46
    עת
    0.45
     leche
    0.45
     aici
    0.45
     اسرائی
    0.44
     mãos
    0.44
     Resultados
    0.44
    Activations Density 0.003%

    No Known Activations