© 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. 130365
    Prev
    Next
    INDEX
    Explanations

    import, get, exception, const

    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
     delaying
    -0.06
     ধরেই
    -0.06
    ச்சை
    -0.06
     combining
    -0.06
    %>
    -0.05
    考えると
    -0.05
    পাঠ
    -0.05
     Without
    -0.05
     outpatient
    -0.05
    फ़ी
    -0.05
    POSITIVE LOGITS
     beispielsweise
    0.07
    一些
    0.06
     bijvoorbeeld
    0.06
    例えば
    0.06
     예를
    0.06
     مثلا
    0.06
     настолько
    0.06
    ફ
    0.06
     максимально
    0.06
     achieve
    0.06
    Activations Density 0.019%

    No Known Activations