© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70271
    Prev
    Next
    INDEX
    Explanations

    men and women

    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
     menangkap
    -1.16
     mengangg
    -1.16
     membag
    -1.14
     memperbaiki
    -1.09
     melindungi
    -1.07
     memeriksa
    -1.06
     membangun
    -1.05
     mengingatkan
    -1.05
     menghilangkan
    -1.02
     menekan
    -1.02
    POSITIVE LOGITS
     women
    6.97
     females
    5.19
    women
    4.78
     men
    4.75
     Women
    4.38
    Women
    4.31
     males
    4.28
     woman
    4.25
     ladies
    4.16
     girls
    4.06
    Activations Density 0.262%

    No Known Activations