© 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. 118096
    Prev
    Next
    INDEX
    Explanations

    titration, allocated, Ethernet, stores

    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
     disg
    -0.06
     பாதுகா
    -0.06
     自分
    -0.06
     ਆਪਣੇ
    -0.06
    openConnection
    -0.06
     اپنے
    -0.05
     病
    -0.05
     כבר
    -0.05
    बिन
    -0.05
     થયા
    -0.05
    POSITIVE LOGITS
    Cannot
    0.07
     motto
    0.07
     similaire
    0.06
     trabalhando
    0.06
    exemple
    0.06
    ..............
    0.06
    常见的
    0.06
    Two
    0.06
     که
    0.06
     работе
    0.06
    Activations Density 0.001%

    No Known Activations