© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80712
    Prev
    Next
    INDEX
    Explanations

    tuxedos and formal wear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     डाल
    -0.76
     mod
    -0.75
     bench
    -0.73
    ToArray
    -0.68
    ﻌ
    -0.68
    yně
    -0.68
     interrogated
    -0.66
     Heimat
    -0.66
    ="<?
    -0.66
    bench
    -0.65
    POSITIVE LOGITS
     tuxedo
    1.61
     tails
    1.41
     evening
    1.18
    uxedo
    1.16
     smoking
    1.14
     Tails
    1.13
     Formal
    1.11
    tails
    1.08
     Smoking
    1.08
    Smoking
    1.05
    Activations Density 0.027%

    No Known Activations