© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21943
    Prev
    Next
    INDEX
    Explanations

    boys and girls

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    健身
    0.55
     корпора
    0.54
     सेक्सी
    0.54
     супру
    0.54
    spouse
    0.52
    🍾
    0.52
    Married
    0.52
    married
    0.50
    性感
    0.50
     স্ত্র
    0.50
    POSITIVE LOGITS
     niño
    1.31
     menino
    1.19
    男孩
    1.16
     الطفل
    1.15
    🧒
    1.14
     criança
    1.13
    👦
    1.13
     boy
    1.13
     meninos
    1.12
     child
    1.11
    Activations Density 0.034%

    No Known Activations