© 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. 116744
    Prev
    Next
    INDEX
    Explanations

    lists of items or sequences

    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
     mientras
    -0.08
     terwijl
    -0.07
     prvi
    -0.07
     먼저
    -0.07
     mentre
    -0.06
     birinci
    -0.06
     Mientras
    -0.06
    ocytic
    -0.06
     divisor
    -0.06
     första
    -0.06
    POSITIVE LOGITS
    athor
    0.07
     eight
    0.06
    auteur
    0.06
    author
    0.06
     three
    0.06
    SelectList
    0.06
     său
    0.06
     itself
    0.06
    lingen
    0.06
    种植
    0.06
    Activations Density 0.001%

    No Known Activations