© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130879
    Prev
    Next
    INDEX
    Explanations

    patent references

    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
     yě
    -0.06
    দশ
    -0.06
     an
    -0.06
     yakni
    -0.06
     имел
    -0.06
     nhằm
    -0.06
    <b>
    -0.06
     outskirts
    -0.05
    বৃত্তি
    -0.05
     supaya
    -0.05
    POSITIVE LOGITS
    Seit
    0.07
     enhances
    0.06
     landscaped
    0.06
     anteriores
    0.06
     이전
    0.06
     ग्राहक
    0.06
     client
    0.06
     trauer
    0.06
     closeness
    0.06
     bhan
    0.06
    Activations Density 0.004%

    No Known Activations