© 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. 129849
    Prev
    Next
    INDEX
    Explanations

    names, numbers, and specific categories

    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
     individuo
    -0.06
     їх
    -0.06
    ine
    -0.06
    “,
    -0.06
    ”،
    -0.06
     அங்கு
    -0.06
     उपयुक्त
    -0.06
     indivíduos
    -0.05
     loro
    -0.05
    ”,
    -0.05
    POSITIVE LOGITS
     three
    0.07
     ceva
    0.07
     two
    0.07
     hmm
    0.07
     খুবই
    0.07
    两大
    0.06
     چیزی
    0.06
     one
    0.06
     terza
    0.06
     ঝামে
    0.06
    Activations Density 0.001%

    No Known Activations