© 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-16K
    7. 9407
    Prev
    Next
    INDEX
    Explanations

    GPU, contest, last year, driving, charging

    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_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
     همین
    0.98
     hereof
    0.91
    鮮
    0.88
    鲜
    0.87
    证
    0.85
     далее
    0.85
     teş
    0.85
    议
    0.81
    ̣
    0.80
    ً
    0.80
    POSITIVE LOGITS
     direttore
    1.55
    Basically
    1.34
    anderen
    1.28
    meng
    1.28
     করিতেছিল
    1.28
     riesce
    1.27
    Arg
    1.26
    cgi
    1.26
     directeur
    1.25
    Weil
    1.25
    Activations Density 0.000%

    No Known Activations