© 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. 2627
    Prev
    Next
    INDEX
    Explanations

    most sites

    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
    0
    1.05
    8
    1.01
    6
    0.97
     червня
    0.93
     ду
    0.91
     звез
    0.91
    7
    0.91
     июня
    0.90
     часа
    0.90
    5
    0.90
    POSITIVE LOGITS
     democracies
    1.65
    大多数
    1.63
    अधिकांश
    1.62
     kebanyakan
    1.62
     umumnya
    1.60
    大多數
    1.57
     modern
    1.53
     humans
    1.49
     çoğu
    1.47
    许多
    1.46
    Activations Density 1.460%

    No Known Activations