© 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. 120016
    Prev
    Next
    INDEX
    Explanations

    part of

    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
     신청
    -0.07
    申请
    -0.07
    申請
    -0.07
     geared
    -0.06
     distint
    -0.06
    每月
    -0.06
     طلب
    -0.06
     intent
    -0.06
    うちに
    -0.06
    请求
    -0.06
    POSITIVE LOGITS
     bị
    0.07
     continuing
    0.06
     received
    0.06
     if
    0.06
     founders
    0.06
     recibido
    0.06
     جامعة
    0.06
     alumna
    0.06
     Some
    0.06
     using
    0.06
    Activations Density 0.004%

    No Known Activations