© 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-65K
    7. 3802
    Prev
    Next
    INDEX
    Explanations

    leaves

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ۵
    1.00
     ک
    0.89
    لا
    0.89
     полости
    0.86
    ༦
    0.85
     اک
    0.85
     افرادی
    0.83
    یک
    0.82
     ۵
    0.82
    หาก
    0.81
    POSITIVE LOGITS
     Leaves
    1.08
    Leaves
    1.02
    F
    0.98
     Leaf
    0.96
    葉
    0.93
     Feuilles
    0.91
     leaves
    0.86
     Leafs
    0.86
    leaves
    0.82
     Blatt
    0.82
    Activations Density 0.028%

    No Known Activations