© 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. 116850
    Prev
    Next
    INDEX
    Explanations

    (function

    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
    名稱
    -0.05
    仍
    -0.05
    不好
    -0.05
    electrode
    -0.05
     대부분
    -0.05
     популяр
    -0.05
     some
    -0.05
     حتى
    -0.05
     certains
    -0.05
     Kuhn
    -0.05
    POSITIVE LOGITS
    이랑
    0.06
     ወይም
    0.06
     ecological
    0.06
     剤
    0.06
     plantes
    0.06
     slump
    0.06
     تقدر
    0.06
     wenn
    0.06
     or
    0.06
     topographic
    0.06
    Activations Density 0.001%

    No Known Activations