© 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. 120637
    Prev
    Next
    INDEX
    Explanations

    digital, smaller, ancient, presidents

    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
     bounty
    -0.06
    Navigation
    -0.06
     путеше
    -0.06
     मृत्यू
    -0.06
     ende
    -0.06
    海拔
    -0.06
    ດ້ານ
    -0.06
     Navigation
    -0.06
     kvalitet
    -0.05
    jap
    -0.05
    POSITIVE LOGITS
     디지털
    0.07
    िनियम
    0.06
     صغير
    0.06
     presiden
    0.06
     जयंती
    0.06
     digitalen
    0.06
     लघु
    0.06
     प्राचीन
    0.06
     smaller
    0.06
     kleiner
    0.06
    Activations Density 0.037%

    No Known Activations