© 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. 117647
    Prev
    Next
    INDEX
    Explanations

    County

    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
    一段时间
    -0.07
     adds
    -0.06
     infuse
    -0.06
     প্রচণ্ড
    -0.06
    служ
    -0.06
     преимущественно
    -0.06
     हैं
    -0.06
     состо
    -0.06
     years
    -0.06
     edhe
    -0.06
    POSITIVE LOGITS
    を
    0.08
     to
    0.06
    த்தின்
    0.06
    それを
    0.06
     கிள
    0.06
    theorem
    0.06
    County
    0.06
     loro
    0.06
    一定是
    0.06
    思い出
    0.06
    Activations Density 0.002%

    No Known Activations