© 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. 116745
    Prev
    Next
    INDEX
    Explanations

    network interface configuration

    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
     तस्वी
    -0.07
     kaleidoscope
    -0.06
    hobby
    -0.06
    Crazy
    -0.06
    Selections
    -0.06
     souvenir
    -0.06
     ভিসা
    -0.06
     shopping
    -0.06
     kuf
    -0.06
     hobby
    -0.06
    POSITIVE LOGITS
     transport
    0.06
     assesses
    0.06
     assess
    0.06
     Electricity
    0.06
    essment
    0.06
    фициа
    0.06
    LinkedList
    0.06
     regulation
    0.06
     preventative
    0.06
     regula
    0.06
    Activations Density 0.004%

    No Known Activations