© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1904
    Prev
    Next
    INDEX
    Explanations

    game

    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
    引起
    1.58
    常常
    1.54
     بن
    1.51
    き
    1.44
     शाळा
    1.42
    眼的
    1.41
    Homework
    1.38
     जनता
    1.37
     Sistemas
    1.36
    
    1.36
    POSITIVE LOGITS
    radi
    1.64
    jali
    1.60
    lardır
    1.38
     fin
    1.37
    ร่าง
    1.33
     jubil
    1.30
    stays
    1.29
     plump
    1.27
    ۰
    1.27
    anze
    1.26
    Activations Density 0.000%

    No Known Activations