© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1548
    Prev
    Next
    INDEX
    Explanations

    past tense of "to be" across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    합니다
    1.37
    Provides
    1.35
     합니다
    1.25
    줍니다
    1.20
    щают
    1.15
    します
    1.14
    вают
    1.14
    봅
    1.08
     Provides
    1.08
     செல்க
    1.07
    POSITIVE LOGITS
     wasn
    3.26
     was
    3.17
    was
    3.17
     buvo
    3.15
     была
    3.06
     הייתה
    3.04
     était
    3.00
     كانت
    2.97
     było
    2.96
     был
    2.91
    Activations Density 0.797%

    No Known Activations