© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130867
    Prev
    Next
    INDEX
    Explanations

    school district or county

    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
     ALL
    -0.06
     besuchen
    -0.06
     обычно
    -0.06
     ব্রিটিশ
    -0.06
     explained
    -0.06
     reçoit
    -0.05
     benefícios
    -0.05
     વધી
    -0.05
    🤔
    -0.05
     prévenir
    -0.05
    POSITIVE LOGITS
    assim
    0.06
    Rather
    0.06
     whose
    0.06
     toasted
    0.06
     городе
    0.06
     ersten
    0.06
    空港
    0.06
     people
    0.06
     خواهند
    0.06
     nisi
    0.06
    Activations Density 0.021%

    No Known Activations