© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10171
    Prev
    Next
    INDEX
    Explanations

    sexual orientation

    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
    Negative Logits
     leech
    1.85
    <unused267>
    1.76
    <unused959>
    1.73
     smudge
    1.73
    蚪
    1.73
     preprint
    1.73
     fluorescent
    1.73
    ᄊ
    1.71
     merhabalar
    1.70
     eager
    1.70
    POSITIVE LOGITS
    iat
    1.36
    i
    1.33
     it
    1.24
    it
    1.23
    up
    1.20
     L
    1.13
     Insurance
    1.12
    It
    1.10
    stige
    1.09
    ь
    1.08
    Activations Density 0.112%

    No Known Activations