© 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. 119692
    Prev
    Next
    INDEX
    Explanations

    version numbers or code snippets

    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
     laughed
    -0.06
     格
    -0.06
     minden
    -0.06
     LEARN
    -0.06
     धान
    -0.06
    ずつ
    -0.06
     gracia
    -0.06
     Verse
    -0.05
    ButtonClicked
    -0.05
    িসে
    -0.05
    POSITIVE LOGITS
     which
    0.06
     dość
    0.06
     WHICH
    0.06
     +
    0.06
    ქვთ
    0.06
    [++
    0.05
     ██
    0.05
     второй
    0.05
     상당히
    0.05
    нутри
    0.05
    Activations Density 0.005%

    No Known Activations