© 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. 170700
    Prev
    Next
    INDEX
    Explanations

    phrases indicating subsequent action or modifiers

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

    questions about choices and exploration

    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
     Customizable
    0.41
     להי
    0.40
     सामना
    0.39
    ി
    0.39
     アウター
    0.39
    കുന്ന
    0.38
     дам
    0.38
    genome
    0.38
    Reverse
    0.38
     Beginner
    0.38
    POSITIVE LOGITS
    สห
    0.50
    ۷
    0.50
    বড়
    0.50
    中国
    0.49
     tujuh
    0.49
     tabel
    0.48
     ری
    0.47
    estead
    0.47
    വരെ
    0.46
    atkar
    0.46
    Activations Density 0.000%

    No Known Activations