© 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. 118547
    Prev
    Next
    INDEX
    Explanations

    un-gnomelike behavior

    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
    完成了
    -0.06
     বন্ধু
    -0.06
    大人
    -0.06
     বন্ধুর
    -0.06
     gotovo
    -0.06
    来了
    -0.06
     impromptu
    -0.06
     ump
    -0.06
     આવ્યો
    -0.06
     अभिनय
    -0.06
    POSITIVE LOGITS
    मारक
    0.07
     each
    0.07
    などに
    0.07
     каждом
    0.07
     however
    0.07
     cuối
    0.07
    seed
    0.07
     každ
    0.06
     każdym
    0.06
     hence
    0.06
    Activations Density 0.004%

    No Known Activations