© 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. 118861
    Prev
    Next
    INDEX
    Explanations

    According to

    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
     GND
    -0.07
    적으로
    -0.07
    ándola
    -0.06
     olmayan
    -0.06
     what
    -0.06
     cinco
    -0.06
    🕗
    -0.06
     пяти
    -0.06
     অনুযায়ী
    -0.06
     пять
    -0.06
    POSITIVE LOGITS
    Before
    0.06
    Rejected
    0.06
     khi
    0.06
     før
    0.06
     Sebelum
    0.06
     ennen
    0.06
     registrant
    0.06
    incredible
    0.06
     sebelum
    0.06
    BUSINESS
    0.06
    Activations Density 0.001%

    No Known Activations