© 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. 118116
    Prev
    Next
    INDEX
    Explanations

    citations like \[[@B2-ijerph-17-04838]

    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
     when
    -0.07
     New
    -0.07
     into
    -0.06
     the
    -0.06
     When
    -0.06
     underground
    -0.06
     if
    -0.06
     Michael
    -0.06
     Peter
    -0.06
     Stephen
    -0.05
    POSITIVE LOGITS
     этому
    0.07
     всему
    0.06
     abhor
    0.06
     $|
    0.06
    plotly
    0.06
    backward
    0.06
     Đối
    0.06
     diesem
    0.06
     clustered
    0.06
     ब्लूटूथ
    0.06
    Activations Density 0.002%

    No Known Activations