© 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. 129336
    Prev
    Next
    INDEX
    Explanations

    OPINION, Olympics, Script

    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
    没了
    -0.07
    MNumber
    -0.06
    ेटिव
    -0.06
     organization
    -0.06
    Service
    -0.06
     UserService
    -0.06
     structured
    -0.06
     ഭാഗ
    -0.05
     temor
    -0.05
     সুন্নত
    -0.05
    POSITIVE LOGITS
    들과
    0.06
    espec
    0.06
     различи
    0.06
     differenza
    0.06
    Utils
    0.06
    מצא
    0.06
     Grands
    0.06
     truthfully
    0.06
     specimens
    0.06
    特别是
    0.06
    Activations Density 0.001%

    No Known Activations