© 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. 117704
    Prev
    Next
    INDEX
    Explanations

    unordered lists

    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
     and
    -0.08
     და
    -0.07
     മറ്റ്
    -0.06
     అ
    -0.06
     এবং
    -0.06
     وكل
    -0.06
     Text
    -0.06
     및
    -0.06
    および
    -0.06
     एवं
    -0.06
    POSITIVE LOGITS
     seemed
    0.06
     only
    0.06
    Containing
    0.06
    Planet
    0.06
     değil
    0.06
    先后
    0.06
    otage
    0.06
     planète
    0.05
    有两个
    0.05
    براير
    0.05
    Activations Density 0.001%

    No Known Activations