© 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. 117174
    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
     añadi
    -0.07
     ચૂંટણી
    -0.06
    abundance
    -0.06
     automobile
    -0.06
    obile
    -0.06
     numerose
    -0.06
     ভয়
    -0.06
    一个个
    -0.06
    した
    -0.06
     heavily
    -0.06
    POSITIVE LOGITS
     known
    0.06
     χρό
    0.06
     !!!
    0.06
    Known
    0.06
    पु
    0.06
     !!
    0.06
    known
    0.06
    !!
    0.05
    .,
    0.05
    संयुक्त
    0.05
    Activations Density 0.000%

    No Known Activations