© 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. 120262
    Prev
    Next
    INDEX
    Explanations

    register signing method

    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
    3
    -0.06
    5
    -0.06
     primero
    -0.05
     đúng
    -0.05
    खुद
    -0.05
    更为
    -0.05
     úspě
    -0.05
     해당
    -0.05
    0
    -0.05
     lagi
    -0.05
    POSITIVE LOGITS
     austere
    0.07
    に行く
    0.07
    ชา
    0.06
     gonna
    0.06
    👖
    0.06
     fornece
    0.06
     சாதாரண
    0.06
    一定会
    0.06
     etab
    0.06
     aau
    0.06
    Activations Density 0.001%

    No Known Activations