© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119526
    Prev
    Next
    INDEX
    Explanations

    past tense verbs followed by a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     continue
    -0.08
     terus
    -0.08
    繼續
    -0.07
     đang
    -0.07
     continues
    -0.07
    继续
    -0.07
    continue
    -0.07
     продолжает
    -0.06
     continuando
    -0.06
     continua
    -0.06
    POSITIVE LOGITS
     três
    0.07
     three
    0.07
     buena
    0.06
    ៣
    0.06
     ofrecemos
    0.06
     여러
    0.06
     ૧
    0.06
     rø
    0.06
    ürm
    0.06
     ausreiche
    0.06
    Activations Density 0.055%

    No Known Activations