© 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. 128352
    Prev
    Next
    INDEX
    Explanations

    DX, dairy, size, introduction

    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
     putative
    -0.06
     tých
    -0.06
    April
    -0.06
     छोड़कर
    -0.06
    更为
    -0.06
    jih
    -0.05
     வேளா
    -0.05
     concili
    -0.05
     extant
    -0.05
     لل
    -0.05
    POSITIVE LOGITS
     last
    0.07
     czyli
    0.07
     یعنی
    0.06
     यानी
    0.06
     that
    0.06
     amigos
    0.06
     আত্মীয়
    0.06
     lee
    0.06
    last
    0.05
     kasus
    0.05
    Activations Density 0.001%

    No Known Activations