© 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. 129978
    Prev
    Next
    INDEX
    Explanations

    industrial source division local

    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
     તેમના
    -0.06
     ihrer
    -0.06
     उनके
    -0.06
    遗憾
    -0.06
     into
    -0.06
     más
    -0.06
     તેમની
    -0.06
     their
    -0.06
    上帝
    -0.06
     terhadap
    -0.05
    POSITIVE LOGITS
     prompted
    0.07
     Автор
    0.07
    大多
    0.06
     devised
    0.06
     usually
    0.06
     largely
    0.06
     penned
    0.06
     Usually
    0.06
    を描
    0.06
     består
    0.06
    Activations Density 0.001%

    No Known Activations