© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1042
    Prev
    Next
    INDEX
    Explanations

    asking to tell me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     znajdują
    0.98
     शेखर
    0.96
    ScrollBar
    0.94
    软件包
    0.93
     Vishal
    0.90
    JlcG
    0.90
    IVACON
    0.89
    
    0.89
     بوتل
    0.89
     マット
    0.89
    POSITIVE LOGITS
     about
    0.97
    about
    0.91
    spoken
    0.86
    一句
    0.85
     something
    0.82
    aboutme
    0.79
     acerca
    0.78
     aloud
    0.77
     πως
    0.77
     bluntly
    0.76
    Activations Density 0.788%

    No Known Activations