© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130878
    Prev
    Next
    INDEX
    Explanations

    :

    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
     sufficiently
    -0.06
    cy
    -0.06
    কুট
    -0.05
     kısm
    -0.05
    contin
    -0.05
     पान
    -0.05
    sh
    -0.05
     seu
    -0.05
    ،
    -0.05
    POSITIVE LOGITS
    从来
    0.07
     rozhod
    0.07
     आमतौर
    0.07
     Pu
    0.07
     никогда
    0.07
     and
    0.06
     एंगल
    0.06
     dengan
    0.06
     Sá
    0.06
     with
    0.06
    Activations Density 0.002%

    No Known Activations