© 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. 211974
    Prev
    Next
    INDEX
    Explanations

    learning and teaching

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

    who will use the app

    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
     સારી
    0.50
     నిర్వహ
    0.48
     একটি
    0.47
     вы
    0.47
     feces
    0.46
    າຍ
    0.46
     विश्वसनीयता
    0.46
     bribery
    0.45
    穏
    0.45
    ‌ನಲ್ಲಿ
    0.45
    POSITIVE LOGITS
    冻
    0.45
    ദി
    0.44
    chre
    0.44
    ValMap
    0.43
     كند
    0.42
     تار
    0.42
     bitrate
    0.41
    ാനാ
    0.41
    金
    0.40
    ritual
    0.40
    Activations Density 0.000%

    No Known Activations