© 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. 129424
    Prev
    Next
    INDEX
    Explanations

    .com URL endings

    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
     lorsque
    -0.07
     even
    -0.07
     sogar
    -0.07
     cuando
    -0.07
     Lorsque
    -0.06
    eeee
    -0.06
     όταν
    -0.06
     argued
    -0.06
     een
    -0.06
     pembangunan
    -0.06
    POSITIVE LOGITS
     reusing
    0.06
    很难
    0.05
     clearest
    0.05
     결과를
    0.05
     ದೇವರ
    0.05
    ன்னை
    0.05
     জমি
    0.05
    重新
    0.05
     Schreib
    0.05
    typical
    0.05
    Activations Density 0.027%

    No Known Activations