© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118326
    Prev
    Next
    INDEX
    Explanations

    end

    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
     whatever
    -0.07
     빨리
    -0.07
    ณะ
    -0.07
     दर्जन
    -0.06
     यूपी
    -0.06
    部は
    -0.06
     فناوری
    -0.06
     হাজার
    -0.06
    arynx
    -0.06
     portion
    -0.06
    POSITIVE LOGITS
    without
    0.06
    もしくは
    0.06
     proactive
    0.06
     yǒu
    0.06
     както
    0.06
    惴
    0.06
     quelquefois
    0.06
    डान
    0.05
     selalu
    0.05
    sometimes
    0.05
    Activations Density 0.002%

    No Known Activations