© 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. 117376
    Prev
    Next
    INDEX
    Explanations

    regular expressions

    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
     for
    -0.07
    1
    -0.06
    2
    -0.06
     medya
    -0.06
    9
    -0.06
     untuk
    -0.05
    For
    -0.05
     kuh
    -0.05
     now
    -0.05
    4
    -0.05
    POSITIVE LOGITS
     الموجود
    0.07
     但
    0.07
     cependant
    0.07
     퇴
    0.06
     HOWEVER
    0.06
     そんな
    0.06
    Однако
    0.06
     Однако
    0.06
     παρου
    0.06
    让我
    0.06
    Activations Density 0.004%

    No Known Activations