© 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. 48439
    Prev
    Next
    INDEX
    Explanations

    creating and defining systems

    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
     urm
    0.45
     financières
    0.43
    ጇ
    0.43
    龙
    0.42
    లువ
    0.41
    计算机
    0.40
    Knowing
    0.40
     administrador
    0.40
     пони
    0.40
    毌
    0.40
    POSITIVE LOGITS
     terroir
    0.48
     گویا
    0.46
     novel
    0.45
     orchards
    0.45
     nõ
    0.45
     agro
    0.44
     sosok
    0.44
     hillside
    0.41
     عام
    0.40
     Māori
    0.40
    Activations Density 0.003%

    No Known Activations