© 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. 129152
    Prev
    Next
    INDEX
    Explanations

    months

    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
     senaste
    -0.06
     warto
    -0.06
     sembra
    -0.06
     menuju
    -0.05
    onomia
    -0.05
    <0xE3>
    -0.05
    ]"
    -0.05
     शू
    -0.05
    どちら
    -0.05
     richied
    -0.05
    POSITIVE LOGITS
    例子
    0.07
     that
    0.07
     intense
    0.06
     Niels
    0.06
     conséquences
    0.06
     basic
    0.06
    FOUR
    0.06
    ?!?
    0.06
     rudimentary
    0.06
     বিলা
    0.06
    Activations Density 0.005%

    No Known Activations