© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178605
    Prev
    Next
    INDEX
    Explanations

    gay social issues

    np_acts-logits-general · gemini-2.5-flash-lite

    "alternatives" , "not"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    pessoas
    0.51
    臃
    0.49
     நிதி
    0.49
    enfants
    0.48
     افرادی
    0.46
     amigos
    0.46
    pessoa
    0.46
    넴
    0.46
    tìm
    0.45
    /*',
    0.45
    POSITIVE LOGITS
    ل
    0.51
    かの
    0.50
     ダブル
    0.45
     docking
    0.45
    l
    0.44
    SH
    0.44
    2
    0.43
    4
    0.43
     dredging
    0.42
    ives
    0.42
    Activations Density 0.000%

    No Known Activations