© 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. 117008
    Prev
    Next
    INDEX
    Explanations

    medical results, programming languages, absence, gloss, options, Ireland, computed tomography, IFN

    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
     Incoming
    -0.06
     हाय
    -0.06
    邱
    -0.05
     coloque
    -0.05
     наиболее
    -0.05
    править
    -0.05
     Proposed
    -0.05
     правильно
    -0.05
    选取
    -0.05
    苣
    -0.05
    POSITIVE LOGITS
     benzer
    0.06
     leçon
    0.06
     from
    0.06
    ounding
    0.06
     absence
    0.06
    ństwo
    0.06
     बोली
    0.06
     يساوي
    0.06
     chieftain
    0.06
     compared
    0.05
    Activations Density 0.063%

    No Known Activations