© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3168
    Prev
    Next
    INDEX
    Explanations

    describing or persuading opinions

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

    Enron, humans, people, reading, birds

    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_53_width_65k_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
     🥰
    0.65
     😘
    0.64
     erstwhile
    0.64
     IMHO
    0.63
     😎
    0.56
     👇
    0.55
    🤣🤣
    0.55
     ;-)
    0.55
     cursory
    0.54
     🤗
    0.54
    POSITIVE LOGITS
     portrays
    0.64
     “[
    0.64
     persu
    0.56
    “[
    0.55
     “‘
    0.52
     persuade
    0.52
     portraying
    0.52
    
    0.51
     সম্বন্ধে
    0.50
     persuading
    0.50
    Activations Density 0.107%

    No Known Activations