© 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. 116307
    Prev
    Next
    INDEX
    Explanations

    text tables with | separators

    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
    :
    -0.06
     your
    -0.06
     a
    -0.06
     you
    -0.06
    you
    -0.06
     soupe
    -0.06
    instruction
    -0.06
     modify
    -0.06
     modifying
    -0.06
     reste
    -0.05
    POSITIVE LOGITS
     only
    0.08
    だけでなく
    0.07
     केवल
    0.07
    केवल
    0.07
     terkenal
    0.06
     اثنين
    0.06
     ليس
    0.06
     только
    0.06
    arrivée
    0.06
    だけ
    0.06
    Activations Density 0.001%

    No Known Activations