© 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. 882
    Prev
    Next
    INDEX
    Explanations

    deny incoming

    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
    англ
    1.37
    面向
    1.33
     центром
    1.29
     aún
    1.27
     także
    1.27
    F
    1.26
     gráfico
    1.25
     scont
    1.23
     graphique
    1.22
     trăm
    1.18
    POSITIVE LOGITS
    itim
    1.72
     harass
    1.71
    egger
    1.70
    otine
    1.58
     本当
    1.58
     こんにちは
    1.57
     Eta
    1.57
     除
    1.57
     把
    1.55
     insist
    1.51
    Activations Density 0.000%

    No Known Activations