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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170218
    Prev
    Next
    INDEX
    Explanations

    St. Basil's Cathedral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     armchair
    0.41
     Clegg
    0.41
    オン
    0.41
    ക്കുറിച്ച
    0.41
    清
    0.40
     framework
    0.40
     chậm
    0.40
     গিল
    0.40
    frameN
    0.39
    LinkClicked
    0.38
    POSITIVE LOGITS
    á
    0.54
     اﻷ
    0.48
     to
    0.47
    vite
    0.46
    uyor
    0.45
    कभी
    0.45
     நேற்று
    0.45
    ானா
    0.43
    MIT
    0.42
    щото
    0.42
    Activations Density 0.010%

    No Known Activations