© 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. 117098
    Prev
    Next
    INDEX
    Explanations

    future, already, different

    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
     when
    -0.06
     tranquill
    -0.06
     देखील
    -0.06
    yarn
    -0.06
     lorsque
    -0.06
    Գ
    -0.06
     vacío
    -0.06
     щоб
    -0.06
    decay
    -0.06
     sudden
    -0.06
    POSITIVE LOGITS
    不同
    0.07
    今後
    0.07
     different
    0.07
    既に
    0.07
    将在
    0.07
     ఇప్పటికే
    0.06
    すでに
    0.06
     разных
    0.06
    将来
    0.06
    いずれ
    0.06
    Activations Density 0.016%

    No Known Activations