© 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. 128367
    Prev
    Next
    INDEX
    Explanations

    foreign language 'only' equivalents

    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
    ดี๋ยว
    -0.06
     گاه
    -0.06
     stockholder
    -0.06
     場合
    -0.06
    ॉरिटी
    -0.06
    happy
    -0.06
    fois
    -0.06
    道路
    -0.06
     bây
    -0.06
     полови
    -0.06
    POSITIVE LOGITS
     only
    0.07
     tikai
    0.07
    만
    0.07
    only
    0.06
     seul
    0.06
     лише
    0.06
     yalnızca
    0.06
     फक्त
    0.06
     mě
    0.06
    のみ
    0.06
    Activations Density 0.001%

    No Known Activations