© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 40342
    Prev
    Next
    INDEX
    Explanations

    figure and axes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     S
    1.00
     Language
    0.99
     D
    0.96
     Ch
    0.95
     Time
    0.93
     Histoire
    0.93
     Y
    0.92
    ='
    0.92
     H
    0.91
     I
    0.90
    POSITIVE LOGITS
     მაშინ
    1.13
     ενός
    1.07
    áp
    1.06
    ższe
    1.06
     thei
    1.05
    ployed
    1.05
     инструменты
    1.05
     द्रविड़
    1.05
    equipped
    1.03
     ਨਹੀਂ
    1.03
    Activations Density 0.025%

    No Known Activations