© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5738
    Prev
    Next
    INDEX
    Explanations

    foreign language scientific terms

    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
     paragraphe
    1.08
     తీసుకొ
    1.05
    たら
    1.04
    ٣
    1.01
    تاء
    1.01
    十七
    1.01
    subsection
    1.01
    Filed
    1.01
     quinze
    1.00
    embrie
    1.00
    POSITIVE LOGITS
     Gu
    1.38
     미래
    1.36
     Rem
    1.35
     可能
    1.34
     다양
    1.34
     Mạnh
    1.32
     K
    1.32
     Gar
    1.31
     당신
    1.29
     Hu
    1.29
    Activations Density 0.002%

    No Known Activations