© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1025
    Prev
    Next
    INDEX
    Explanations

    actions involving data or state

    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_22_width_16k_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
     每个
    1.16
     शकत
    1.11
     画像
    1.09
     సినిమాలో
    1.08
     주로
    1.07
     我
    1.05
    Vertices
    1.04
    每个
    1.03
     你
    1.03
     वेगवेगळ्या
    1.02
    POSITIVE LOGITS
     things
    1.99
     matters
    1.67
    Things
    1.61
     Things
    1.59
     proceedings
    1.56
    things
    1.54
     Dinge
    1.51
     hostilities
    1.46
     THINGS
    1.36
     choses
    1.33
    Activations Density 1.200%

    No Known Activations