© 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. 128885
    Prev
    Next
    INDEX
    Explanations

    west of

    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
    ;
    -0.06
    primary
    -0.06
     current
    -0.06
    而在
    -0.06
     primary
    -0.06
    single
    -0.05
    二
    -0.05
    partial
    -0.05
    年在
    -0.05
    均为
    -0.05
    POSITIVE LOGITS
     там
    0.06
     отказа
    0.06
     bikes
    0.06
     प्रतिबद्ध
    0.06
     podej
    0.06
     ricevuto
    0.06
    achtig
    0.06
    キュー
    0.06
     różnych
    0.06
     Gefühl
    0.06
    Activations Density 0.001%

    No Known Activations