© 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. 129271
    Prev
    Next
    INDEX
    Explanations

    listing or general terms

    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
     yöntem
    -0.06
     सुधार
    -0.06
     three
    -0.06
    entre
    -0.05
    rio
    -0.05
     कहला
    -0.05
     Repairs
    -0.05
    垢
    -0.05
    向けの
    -0.05
     four
    -0.05
    POSITIVE LOGITS
    eload
    0.07
     الاشكال
    0.07
     automata
    0.06
            
    0.06
    कृत
    0.06
    ↵↵
    0.06
     noting
    0.06
     vào
    0.06
     экономи
    0.06
     kein
    0.06
    Activations Density 0.001%

    No Known Activations