© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9179
    Prev
    Next
    INDEX
    Explanations

    how to run code

    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
     sekaligus
    0.98
     대해서
    0.96
     وكان
    0.96
    :@
    0.92
    etzten
    0.91
     وكانت
    0.91
     beinh
    0.90
     içeren
    0.90
    ajati
    0.89
    と考えられる
    0.87
    POSITIVE LOGITS
     hindsight
    1.32
     luck
    1.19
     careful
    1.14
     each
    1.13
     mỗi
    1.07
    Each
    1.02
    时间的
    1.01
    每一次
    1.00
    每
    1.00
     practice
    0.97
    Activations Density 0.085%

    No Known Activations