© 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. 118491
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     घायल
    -0.06
     injury
    -0.06
     ikke
    -0.06
    Injury
    -0.06
     injure
    -0.06
    inj
    -0.06
     danno
    -0.06
     enough
    -0.06
     رپورٹ
    -0.06
     chronicles
    -0.06
    POSITIVE LOGITS
     continuidad
    0.06
     kijk
    0.06
     প্রযুক্ত
    0.06
    更加
    0.06
    ፈጥ
    0.06
     with
    0.06
    దేశ
    0.06
     ujung
    0.06
     informática
    0.06
     contradd
    0.06
    Activations Density 0.000%

    No Known Activations