© 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. 130091
    Prev
    Next
    INDEX
    Explanations

    items worn for covering or protection

    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
     doxy
    -0.07
     Consulate
    -0.07
     camping
    -0.06
     einschließlich
    -0.06
     substantial
    -0.06
     employers
    -0.06
     వ్యక్
    -0.06
     exempted
    -0.06
    exclude
    -0.06
     expensive
    -0.06
    POSITIVE LOGITS
     would
    0.07
     serait
    0.06
    इद
    0.06
     हुन्छ
    0.06
     Afterward
    0.06
     olisi
    0.06
     Nt
    0.06
     first
    0.06
    first
    0.06
     Orders
    0.06
    Activations Density 0.013%

    No Known Activations