© 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. 6726
    Prev
    Next
    INDEX
    Explanations

    comfort

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

    comfort

    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
     সত্যা
    0.41
    炝
    0.39
     STRONG
    0.38
    㸮
    0.38
     قانونی
    0.37
     হত্যাকাণ্ড
    0.37
    dangerous
    0.37
    দ্রোহ
    0.36
    筮
    0.36
    STRONG
    0.36
    POSITIVE LOGITS
     comfort
    3.92
    comfort
    3.44
     Comfort
    3.38
     confort
    3.19
     comforts
    3.19
     komfort
    3.16
    Comfort
    3.14
     комфор
    3.11
     conforto
    3.03
     comodidad
    3.00
    Activations Density 0.154%

    No Known Activations