Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12138
    Prev
    Next
    INDEX
    Explanations

    sexual communication and mating

    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_31_width_16k_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
    ന്റ്
    0.55
    贵
    0.52
     Monetary
    0.52
    Businesses
    0.52
     Championships
    0.51
     मार्केट
    0.51
    玑
    0.51
     页
    0.50
     તમારી
    0.50
     Businesses
    0.50
    POSITIVE LOGITS
     survival
    0.63
     anten
    0.61
     survive
    0.61
     males
    0.59
     gland
    0.59
     secretion
    0.59
     sexual
    0.58
     regulate
    0.57
     physiological
    0.57
     adaptive
    0.57
    Activations Density 0.271%

    No Known Activations