© 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. 128558
    Prev
    Next
    INDEX
    Explanations

    understanding peptide chemistry or biology

    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
     значи
    -0.07
     on
    -0.06
     அல்ல
    -0.06
     away
    -0.06
     bedeut
    -0.06
    纜
    -0.06
     그다음에
    -0.06
     иных
    -0.06
     два
    -0.06
     significant
    -0.06
    POSITIVE LOGITS
     ప్రశ్న
    0.06
    “”
    0.06
     दुर्भाग्य
    0.06
     showed
    0.06
    unfortunately
    0.06
    ‘’
    0.06
    Unfortunately
    0.06
    由于
    0.06
    aggressive
    0.06
     nawet
    0.06
    Activations Density 0.002%

    No Known Activations