© 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-16K
    7. 6391
    Prev
    Next
    INDEX
    Explanations

    recommendations

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ेक्षा
    0.42
    Freight
    0.41
    营销
    0.41
    emonic
    0.41
    マーケ
    0.39
     खतरे
    0.39
     कुर्बानी
    0.39
     uploading
    0.39
     risking
    0.39
    
    0.39
    POSITIVE LOGITS
    推荐
    0.64
     Recommendations
    0.60
     recommend
    0.60
     recommendations
    0.59
    Recommendations
    0.58
     Recommend
    0.57
    recommend
    0.57
     recomendaciones
    0.55
     recommandations
    0.55
     recomendar
    0.54
    Activations Density 0.092%

    No Known Activations