© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 2626
    Prev
    Next
    INDEX
    Explanations

    program keywords and file paths

    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_7_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
     黑
    4.06
     其他
    3.93
     餐
    3.89
     我的
    3.80
     啊
    3.75
     程序
    3.74
     不是
    3.72
     每
    3.72
     花
    3.71
     套
    3.70
    POSITIVE LOGITS
     लगाएंगे
    2.83
     necesitar
    2.74
    टेगरी
    2.68
    क्रोस
    2.63
    tidak
    2.62
     ampla
    2.60
     करिएगा
    2.59
     velocidade
    2.59
     लगेंगे
    2.59
     पहुँचा
    2.57
    Activations Density 0.208%

    No Known Activations