© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85377
    Prev
    Next
    INDEX
    Explanations

    media and contact information

    np_acts-logits-general · gemini-2.5-flash-lite

    press contacts and information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ၿ
    0.46
    newInstance
    0.46
     optimizes
    0.43
     fournir
    0.42
     unveils
    0.41
     Ubuy
    0.41
     슈
    0.40
     offrir
    0.40
    保証
    0.40
    ماية
    0.40
    POSITIVE LOGITS
                                   
    0.53
     MEDIA
    0.52
     मीडिया
    0.52
     media
    0.50
     коммента
    0.50
     మీడియా
    0.50
            
    0.49
     графи
    0.47
     фото
    0.47
     attached
    0.46
    Activations Density 0.031%

    No Known Activations