© 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. 129074
    Prev
    Next
    INDEX
    Explanations

    switching, up, in, Introduction, live

    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
     প্রকৃত
    -0.07
    varying
    -0.07
     স্বভাব
    -0.07
     соблю
    -0.06
     आमतौर
    -0.06
     অধিকাংশ
    -0.06
     다르
    -0.06
     differences
    -0.06
     differentiation
    -0.06
     разных
    -0.06
    POSITIVE LOGITS
     urging
    0.07
    有利于
    0.07
     impetus
    0.06
     scientifically
    0.06
     fastened
    0.06
     மேம்ப
    0.06
     advantageous
    0.06
     aprov
    0.06
     Acceleration
    0.06
     proposal
    0.06
    Activations Density 0.002%

    No Known Activations