© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 47621
    Prev
    Next
    INDEX
    Explanations

    gender expression or identity

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     angulis
    0.49
    钎
    0.41
    自己在
    0.40
     ConsoleKey
    0.40
     sank
    0.39
     Sank
    0.39
     свой
    0.38
    rcode
    0.38
    epar
    0.38
    sbParams
    0.36
    POSITIVE LOGITS
     potent
    0.44
    表达
    0.41
    表現
    0.40
    ত
    0.39
    preserved
    0.38
    ParameterActive
    0.38
     material
    0.37
    אי
    0.37
    )}+\
    0.36
     version
    0.36
    Activations Density 0.001%

    No Known Activations