© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99116
    Prev
    Next
    INDEX
    Explanations

    descriptors for men

    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
     memutus
    -1.22
     menyiapkan
    -1.12
     menetapkan
    -1.09
     memasang
    -1.07
     mengumpulkan
    -1.05
     menyelesaikan
    -1.03
     membangun
    -1.03
     menekan
    -1.02
     mengajak
    -1.00
     memeriksa
    -0.98
    POSITIVE LOGITS
     man
    6.38
     men
    4.47
     woman
    3.22
     homem
    3.19
    男人
    3.13
    uomo
    3.02
     uomo
    2.86
     hombre
    2.83
     الرجل
    2.69
     homens
    2.59
    Activations Density 0.155%

    No Known Activations