© 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. 119595
    Prev
    Next
    INDEX
    Explanations

    overview of

    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
    家族
    -0.07
     quarantined
    -0.06
    ዉ
    -0.06
    မ
    -0.06
     Bruges
    -0.06
    Routes
    -0.06
    目的地
    -0.06
     Riggs
    -0.06
     mating
    -0.06
     유럽
    -0.06
    POSITIVE LOGITS
     मोठ
    0.06
     zehn
    0.06
    厲
    0.06
    ress
    0.06
    嘭
    0.05
     জরুরি
    0.05
     calyce
    0.05
     يعني
    0.05
     Mean
    0.05
     zašt
    0.05
    Activations Density 0.001%

    No Known Activations