© 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. 117143
    Prev
    Next
    INDEX
    Explanations

    locations, news, career, or Q&A context

    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
     their
    -0.08
     Jones
    -0.06
     jeho
    -0.06
     makes
    -0.06
     keine
    -0.06
     খানকে
    -0.06
    τικών
    -0.06
     kuten
    -0.06
     कभी
    -0.05
     quelques
    -0.05
    POSITIVE LOGITS
        
    0.07
    它可以
    0.06
    先の
    0.06
     locus
    0.06
     précédemment
    0.06
    最早
    0.06
     afet
    0.06
     предыду
    0.06
     intensification
    0.06
     nearby
    0.06
    Activations Density 0.001%

    No Known Activations