© 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. 119235
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and simplification

    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
     tặng
    -0.07
    恥
    -0.06
     situações
    -0.06
     responsabilité
    -0.06
     sponsored
    -0.06
    egna
    -0.06
     Ат
    -0.06
    =
    -0.06
    source
    -0.06
     incontinence
    -0.06
    POSITIVE LOGITS
     still
    0.08
     ближай
    0.06
     পরিষদে
    0.06
     judgment
    0.06
    我们
    0.06
    Still
    0.06
    still
    0.06
     Judgment
    0.06
     তখনও
    0.06
     സഹായി
    0.06
    Activations Density 0.002%

    No Known Activations