© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118406
    Prev
    Next
    INDEX
    Explanations

    help get the most

    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
     means
    -0.06
    ֶ
    -0.06
     Anti
    -0.06
     full
    -0.06
    மான
    -0.06
    必要的
    -0.06
    人们
    -0.05
    全
    -0.05
    ective
    -0.05
    เช่น
    -0.05
    POSITIVE LOGITS
    loving
    0.07
     použív
    0.06
     இதுவரை
    0.06
     користу
    0.06
     کبھی
    0.06
     giúp
    0.06
     весьма
    0.06
    loos
    0.06
     ప్రస్తుతం
    0.06
     futuras
    0.06
    Activations Density 0.033%

    No Known Activations