© 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. 119275
    Prev
    Next
    INDEX
    Explanations

    semicolon formatting

    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
     तपास
    -0.06
     hız
    -0.06
     झाल्यावर
    -0.06
    isierten
    -0.06
    fruits
    -0.06
     multiplier
    -0.06
    滑
    -0.06
    マー
    -0.06
    路上
    -0.06
     navigational
    -0.06
    POSITIVE LOGITS
     diameter
    0.06
     잘못
    0.06
     botched
    0.06
     misunder
    0.06
     coexist
    0.06
     बिल
    0.06
     Acrylic
    0.06
     pair
    0.05
    所谓的
    0.05
     There
    0.05
    Activations Density 0.001%

    No Known Activations