© 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. 9638
    Prev
    Next
    INDEX
    Explanations

    skills and experiences

    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
    并通过
    1.00
    jd
    0.99
     vlast
    0.90
     digamos
    0.90
    ០
    0.89
     kuten
    0.88
    瑀
    0.88
    சே
    0.88
    摖
    0.88
    網友
    0.87
    POSITIVE LOGITS
     if
    2.02
     اذا
    1.79
     wenn
    1.78
     إذا
    1.71
     apabila
    1.70
    if
    1.66
     если
    1.63
     jika
    1.59
     quando
    1.57
     when
    1.56
    Activations Density 0.416%

    No Known Activations