© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5939
    Prev
    Next
    INDEX
    Explanations

    length measurements

    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
    2.93
     沙
    2.93
     don
    2.89
     套
    2.86
     黑
    2.84
     啊
    2.81
     就是
    2.79
     grab
    2.75
     π
    2.71
     guard
    2.70
    POSITIVE LOGITS
    Tidak
    4.58
    tidak
    4.56
    În
    4.46
    Dalam
    4.37
    Selain
    4.33
    На
    4.17
    Sementara
    4.11
    Pokud
    4.09
    Untuk
    4.09
    Ко
    4.08
    Activations Density 1.957%

    No Known Activations