© 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. 71354
    Prev
    Next
    INDEX
    Explanations

    phrases with followed tokens

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

    list classification

    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
    лав
    0.46
    нию
    0.46
     scanners
    0.45
    Therates
    0.44
    わ
    0.44
     insieme
    0.43
    льно
    0.43
    خلص
    0.43
    りに
    0.42
    Ani
    0.42
    POSITIVE LOGITS
     Vegetarian
    0.51
     각각
    0.48
    ът
    0.47
     प्रत्ये
    0.46
     মঞ্জ
    0.43
     Stage
    0.43
     পরবর্তীতে
    0.43
    痠
    0.43
     ასევე
    0.43
     Manipulation
    0.43
    Activations Density 0.000%

    No Known Activations