© 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. 120099
    Prev
    Next
    INDEX
    Explanations

    questions or code sections

    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
     cael
    -0.07
    typ
    -0.06
     تعدد
    -0.06
    iko
    -0.06
    getting
    -0.06
    жет
    -0.06
    قدر
    -0.06
     ناب
    -0.05
    vä
    -0.05
     Papua
    -0.05
    POSITIVE LOGITS
     expressway
    0.10
     highway
    0.07
    ujemy
    0.07
     motorway
    0.07
     nếu
    0.06
     Expressway
    0.06
    ного
    0.06
     Bike
    0.06
     bike
    0.06
     amigo
    0.06
    Activations Density 0.005%

    No Known Activations