© 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. 120263
    Prev
    Next
    INDEX
    Explanations

    and followed by nouns

    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
    みに
    -0.06
     COMPUT
    -0.06
     cannot
    -0.06
    hatta
    -0.06
    た
    -0.05
    ides
    -0.05
    roa
    -0.05
     Universal
    -0.05
     голос
    -0.05
     whatever
    -0.05
    POSITIVE LOGITS
    -\{
    0.06
    럼
    0.06
     presentes
    0.06
     différence
    0.06
     છ
    0.06
    决心
    0.06
    ográf
    0.05
     whilst
    0.05
     отличие
    0.05
     difer
    0.05
    Activations Density 0.019%

    No Known Activations