© 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. 118081
    Prev
    Next
    INDEX
    Explanations

    npm install

    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
    了
    -0.07
    തം
    -0.07
     kecuali
    -0.07
     recomendaciones
    -0.07
     ਵੀ
    -0.06
     dictates
    -0.06
    waarden
    -0.06
     policewomen
    -0.06
     conforms
    -0.06
    áles
    -0.06
    POSITIVE LOGITS
    ⏱
    0.06
     monitoring
    0.06
     an
    0.06
    <0xE2>
    0.06
     dual
    0.05
    tri
    0.05
     The
    0.05
     at
    0.05
     огромное
    0.05
     both
    0.05
    Activations Density 0.004%

    No Known Activations