© 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. 118040
    Prev
    Next
    INDEX
    Explanations

    software and documentation

    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
     activated
    -0.07
     methods
    -0.06
     instructions
    -0.06
     способы
    -0.06
    操作
    -0.06
     -(
    -0.06
     либо
    -0.06
     you
    -0.06
     operate
    -0.06
    दिशा
    -0.06
    POSITIVE LOGITS
     appendage
    0.07
     describing
    0.07
     presenting
    0.06
     추가
    0.06
     adipiscing
    0.06
    ispens
    0.06
     এত
    0.06
     presentato
    0.06
     noct
    0.06
     Descriptive
    0.06
    Activations Density 0.001%

    No Known Activations