© 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. 40-GEMMASCOPE-2-RES-65K
    7. 47341
    Prev
    Next
    INDEX
    Explanations

    sales floor or court

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ்க
    0.39
     crosstalk
    0.37
    ']
    0.37
     fécond
    0.36
     developmental
    0.36
    妊娠
    0.35
    にも
    0.34
     Gerry
    0.34
     Sitt
    0.34
     বিগ
    0.34
    POSITIVE LOGITS
    ในสนาม
    1.07
    场
    1.06
     field
    1.03
     मैदान
    1.03
     battlefield
    1.03
     onstage
    1.02
     lapangan
    0.97
    フィールド
    0.95
     মাঠে
    0.91
     میدان
    0.91
    Activations Density 0.040%

    No Known Activations