© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2023
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    rame
    0.58
    壕
    0.47
    estre
    0.45
    耻
    0.44
    แหน
    0.43
    IFEST
    0.41
     muß
    0.40
    ester
    0.39
    貫
    0.39
     stile
    0.37
    POSITIVE LOGITS
     AI
    3.03
    AI
    2.88
     chatbots
    2.83
    人工智能
    2.80
     ChatGPT
    2.65
     chatbot
    2.58
    🤖
    2.57
    ChatGPT
    2.57
     Robots
    2.53
     Artificial
    2.53
    Activations Density 5.106%

    No Known Activations