© 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. 129371
    Prev
    Next
    INDEX
    Explanations

    foreign language prepositions and conjunctions

    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
     cockroaches
    -0.06
    delivery
    -0.06
     outfits
    -0.06
    Ọ
    -0.06
     chúng
    -0.06
     لازم
    -0.06
     सी
    -0.06
     प्रश्
    -0.06
    茏
    -0.06
     তারা
    -0.06
    POSITIVE LOGITS
     desde
    0.07
     without
    0.07
     whilst
    0.06
     без
    0.06
     vanaf
    0.06
     depuis
    0.06
     Desde
    0.06
     χωρίς
    0.06
    desde
    0.05
    來
    0.05
    Activations Density 0.001%

    No Known Activations