© 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. 118416
    Prev
    Next
    INDEX
    Explanations

    constitution clause

    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
    經過
    -0.06
    天上
    -0.06
    리
    -0.06
    后面的
    -0.06
     downright
    -0.06
    這是
    -0.06
    ంటీ
    -0.06
    明らかに
    -0.06
    上面的
    -0.06
    Restrictions
    -0.06
    POSITIVE LOGITS
     etwas
    0.06
     굉장
    0.06
    等多
    0.06
     इन्हे
    0.06
    等を
    0.06
    程度
    0.06
     notoriously
    0.06
     intertw
    0.06
     pradesh
    0.05
     Blot
    0.05
    Activations Density 0.001%

    No Known Activations