© 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. 117612
    Prev
    Next
    INDEX
    Explanations

    more compact

    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
     offers
    -0.07
     그녀
    -0.06
     oferece
    -0.06
    -.
    -0.06
     offerings
    -0.06
     Kitchen
    -0.06
     altering
    -0.06
     nawet
    -0.06
    orden
    -0.06
     ofere
    -0.06
    POSITIVE LOGITS
    ไม่มี
    0.06
    可谓
    0.06
    ဖြင့်
    0.06
     accordingly
    0.06
    於是
    0.06
     так
    0.06
    quiet
    0.06
    所谓
    0.06
    因此
    0.06
     চিকিৎসার
    0.06
    Activations Density 0.016%

    No Known Activations