© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11492
    Prev
    Next
    INDEX
    Explanations

    what is drag queens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ઙ
    2.35
    õe
    2.15
     pośred
    2.15
     engender
    2.14
    人民
    2.11
    št
    2.11
    étera
    2.10
     Ekonomi
    2.10
     memahami
    2.04
     bhave
    2.01
    POSITIVE LOGITS
    ത്തിയ
    1.63
     knobs
    1.56
    an
    1.53
    貯
    1.39
    locking
    1.38
     snatch
    1.37
     swinging
    1.36
     tube
    1.36
     stick
    1.34
     pictures
    1.33
    Activations Density 0.000%

    No Known Activations