© 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. 120306
    Prev
    Next
    INDEX
    Explanations

    package, JAR, MF

    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
    であろう
    -0.07
    اا
    -0.07
    planning
    -0.07
     телеви
    -0.06
     verursacht
    -0.06
     dehuman
    -0.06
     publicly
    -0.06
     públic
    -0.06
     hearings
    -0.06
    emulator
    -0.06
    POSITIVE LOGITS
     biotech
    0.06
     उद्योग
    0.06
     avons
    0.06
     disrupt
    0.05
     inlaid
    0.05
    pack
    0.05
    (_.
    0.05
     kwenye
    0.05
     doanh
    0.05
    ok
    0.05
    Activations Density 0.002%

    No Known Activations