© 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. 129178
    Prev
    Next
    INDEX
    Explanations

    scientific and technical phrases

    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
    ská
    -0.06
       
    -0.05
     અને
    -0.05
    하면서
    -0.05
    qa
    -0.05
    ধ্যে
    -0.05
    菉
    -0.05
     nikdy
    -0.05
     would
    -0.05
     に
    -0.05
    POSITIVE LOGITS
     monotonically
    0.07
     chronological
    0.06
     wet
    0.06
     наконец
    0.06
     monotonic
    0.06
     unique
    0.06
     appreciable
    0.06
     unrival
    0.06
     kN
    0.06
    obatan
    0.06
    Activations Density 0.006%

    No Known Activations