© 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. 6978
    Prev
    Next
    INDEX
    Explanations

    colors and code

    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
    امہ
    1.31
    ान
    1.28
    y
    1.24
    an
    1.24
     μιας
    1.19
    ことができます
    1.19
    m
    1.18
    ashe
    1.18
    t
    1.14
    n
    1.12
    POSITIVE LOGITS
    특히
    1.76
     szczególnie
    1.48
    лә
    1.47
     sobretudo
    1.47
    łego
    1.45
     särsk
    1.44
    ລັບ
    1.44
    ەند
    1.44
    헨
    1.44
     definisi
    1.43
    Activations Density 0.042%

    No Known Activations