© 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. 117546
    Prev
    Next
    INDEX
    Explanations

    raulston

    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
     chloro
    -0.06
     pull
    -0.06
     puedas
    -0.06
    QRY
    -0.05
    嗄
    -0.05
    йга
    -0.05
     their
    -0.05
     apportion
    -0.05
    colour
    -0.05
     faça
    -0.05
    POSITIVE LOGITS
     temporary
    0.06
     обладает
    0.06
     high
    0.06
     sparked
    0.06
     savoir
    0.06
    മാണ
    0.06
     azonban
    0.06
     naquela
    0.06
     него
    0.06
     البيان
    0.06
    Activations Density 0.012%

    No Known Activations