© 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. 117667
    Prev
    Next
    INDEX
    Explanations

    back, charter, ward, annex

    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
    jadi
    -0.06
     पटाखों
    -0.06
    geois
    -0.06
    感觉
    -0.06
     conglomer
    -0.06
     collected
    -0.06
     aggregated
    -0.06
    ಿಗಳ
    -0.06
    都是
    -0.06
     simpler
    -0.06
    POSITIVE LOGITS
     восстанов
    0.06
    ASSIGN
    0.06
    收款
    0.06
     गया
    0.06
     restorations
    0.06
    恢復
    0.06
    争议
    0.06
     sprayed
    0.06
     должны
    0.06
    शिता
    0.06
    Activations Density 0.017%

    No Known Activations