© 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. 4066
    Prev
    Next
    INDEX
    Explanations

    brands, species, growth, natural

    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
    `/
    2.05
     народного
    1.96
    𝓮
    1.78
     Nación
    1.77
    वरों
    1.72
     عندنا
    1.71
    рал
    1.71
     nulla
    1.68
    presentable
    1.67
    绔
    1.67
    POSITIVE LOGITS
    Sa
    1.51
     spirit
    1.48
    нце
    1.42
     Sa
    1.35
    yny
    1.35
    MART
    1.34
     Co
    1.33
    eous
    1.30
    Ano
    1.30
     Lie
    1.28
    Activations Density 0.000%

    No Known Activations