© 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. 118558
    Prev
    Next
    INDEX
    Explanations

    .

    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
     their
    -0.07
     дуже
    -0.06
     hará
    -0.06
     너무
    -0.06
     मतगणना
    -0.06
     Joan
    -0.05
     صعب
    -0.05
     meinem
    -0.05
     इस्तेमाल
    -0.05
    inet
    -0.05
    POSITIVE LOGITS
    失去
    0.06
    CLUSTERED
    0.06
     rethink
    0.06
    我们可以
    0.06
     tersebut
    0.06
    缩小
    0.06
    淢
    0.05
     కొంత
    0.05
    These
    0.05
     पती
    0.05
    Activations Density 0.022%

    No Known Activations