© 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. 116479
    Prev
    Next
    INDEX
    Explanations

    category archives

    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
     changed
    -0.06
     asserted
    -0.06
    Among
    -0.06
    ワゴン
    -0.06
     організа
    -0.05
    ў
    -0.05
     datang
    -0.05
     термин
    -0.05
     attr
    -0.05
     began
    -0.05
    POSITIVE LOGITS
    ➕
    0.07
     possible
    0.07
     possibles
    0.07
    ড়িয়ে
    0.07
     corresponding
    0.07
     posibles
    0.06
    possible
    0.06
     possibilities
    0.06
     возможных
    0.06
     werken
    0.06
    Activations Density 0.001%

    No Known Activations