© 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. 203005
    Prev
    Next
    INDEX
    Explanations

    work to

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

    AMOLED screens

    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
     coalgebras
    0.47
     spain
    0.47
     decidido
    0.46
     interstitiis
    0.46
     setembro
    0.46
    ﻙ
    0.45
    ्मण
    0.44
     oku
    0.44
     traced
    0.44
    рас
    0.44
    POSITIVE LOGITS
     اجرای
    0.46
     还
    0.46
    而是
    0.45
    Idle
    0.41
    能够在
    0.41
     বান্ধবী
    0.41
    劳
    0.41
    懒
    0.41
    娅
    0.41
    ElementChild
    0.41
    Activations Density 0.000%

    No Known Activations