© 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. 129201
    Prev
    Next
    INDEX
    Explanations

    Polish county names

    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
     необходимые
    -0.06
     Arbeit
    -0.06
     מכ
    -0.06
     potrebné
    -0.06
     فکر
    -0.06
     किसकी
    -0.06
     cirrhosis
    -0.06
     Rydberg
    -0.06
     dunes
    -0.06
    though
    -0.05
    POSITIVE LOGITS
     we
    0.06
    看完
    0.06
     remarkable
    0.06
     overwhelm
    0.06
    =="
    0.06
    我們
    0.06
    เรา
    0.06
     VERY
    0.06
     has
    0.06
    アラ
    0.06
    Activations Density 0.042%

    No Known Activations