© 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. 4384
    Prev
    Next
    INDEX
    Explanations

    AI, chatbots, robots

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

    AI, assistant, mate, current

    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
     ወቅ
    0.42
    蒺
    0.40
    ylethyl
    0.39
     localVarAccept
    0.38
    SwingConstants
    0.37
     традиции
    0.37
     secular
    0.36
    कांची
    0.36
    ತ್ರೆ
    0.36
    ᱴ
    0.36
    POSITIVE LOGITS
     AI
    2.61
    人工智能
    2.47
    AI
    2.25
     Artificial
    2.20
     chatbots
    2.16
    Artificial
    2.11
     robot
    2.06
     आर्टिफिशियल
    2.06
     chatbot
    2.05
     robots
    2.03
    Activations Density 0.247%

    No Known Activations