© 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. 118228
    Prev
    Next
    INDEX
    Explanations

    publications, creation, authorship

    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
    ぜ
    -0.07
    💥
    -0.06
    foo
    -0.06
     street
    -0.06
     مثال
    -0.06
    াকিং
    -0.06
    ictured
    -0.06
    からです
    -0.06
    私たちの
    -0.06
    だったので
    -0.06
    POSITIVE LOGITS
     selected
    0.07
    又要
    0.07
     lại
    0.06
     efficiencies
    0.06
     Even
    0.06
    各国
    0.06
     musí
    0.06
     nicht
    0.06
     nuovamente
    0.06
     उत्कृष्टता
    0.06
    Activations Density 0.002%

    No Known Activations