© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118413
    Prev
    Next
    INDEX
    Explanations

    `Q:`, `Tag:`, `Effect:`

    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
     시간에는
    -0.07
    administrator
    -0.07
     Джор
    -0.06
    messer
    -0.06
     Alabama
    -0.06
     জর্জ
    -0.06
    不懂
    -0.06
    緋
    -0.06
     catfish
    -0.06
    即使
    -0.06
    POSITIVE LOGITS
     hockey
    0.07
    Reason
    0.06
    Vancouver
    0.06
     pequeña
    0.06
    hockey
    0.06
     Winnipeg
    0.06
     pequeñas
    0.06
     reasonable
    0.06
    orks
    0.06
    Open
    0.06
    Activations Density 0.023%

    No Known Activations