© 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. 117582
    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
    和
    -0.07
    และ
    -0.07
     и
    -0.06
    _(
    -0.06
     και
    -0.06
     chegar
    -0.06
     তুলেছে
    -0.06
     और
    -0.06
     কার্ড
    -0.06
     és
    -0.06
    POSITIVE LOGITS
     continuously
    0.07
     continually
    0.07
     a
    0.07
     sami
    0.06
     அப்படி
    0.06
     electrically
    0.06
     entièrement
    0.06
     from
    0.06
     dụng
    0.06
    뭡
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.