© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 119006
    Prev
    Next
    INDEX
    Explanations

    CR citations

    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
     слегка
    -0.06
     Даже
    -0.06
     सिर्फ
    -0.06
     за
    -0.06
     خلف
    -0.06
     rump
    -0.06
     arrière
    -0.06
     králov
    -0.06
    ="$(
    -0.06
     추가
    -0.06
    POSITIVE LOGITS
     waves
    0.06
    たちの
    0.06
     begging
    0.06
     বিভিন্ন
    0.06
     గురించి
    0.06
     সংক্রান্ত
    0.06
    datum
    0.06
     analysing
    0.05
     Kare
    0.05
     sedimentary
    0.05
    Activations Density 0.001%

    No Known Activations