© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162060
    Prev
    Next
    INDEX
    Explanations

    Primary Parent or guardian

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

    dynamic resizing or assignment

    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
    Not in Any Lists

    No Comments

    Negative Logits
     matrimonial
    0.52
    ‌‌
    0.49
    どう
    0.47
    ου
    0.47
    사인
    0.46
    Scha
    0.46
    Xiaomi
    0.45
    UTC
    0.45
    衡
    0.44
     quot
    0.43
    POSITIVE LOGITS
     えっと
    0.55
     Appendix
    0.55
     сн
    0.55
     Conjecture
    0.52
     ä
    0.52
     к
    0.52
     факт
    0.52
     erfolgre
    0.51
    cluso
    0.49
    एनएल
    0.49
    Activations Density 0.000%

    No Known Activations