© 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. 128422
    Prev
    Next
    INDEX
    Explanations

    event handling and definitions

    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
     liberdade
    -0.06
    Chiesa
    -0.06
     자유
    -0.06
    عم
    -0.06
    意味着
    -0.06
     luxe
    -0.06
     gunakan
    -0.06
     townhouse
    -0.06
     liberté
    -0.06
    Locked
    -0.06
    POSITIVE LOGITS
     KNOW
    0.06
    จะ
    0.06
     YOUR
    0.06
    inducing
    0.06
     Become
    0.06
    normalized
    0.06
    或其他
    0.05
     virulent
    0.05
     สื
    0.05
     WOULD
    0.05
    Activations Density 0.002%

    No Known Activations