© 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. 117982
    Prev
    Next
    INDEX
    Explanations

    aircraft names and locations

    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
     electricity
    -0.06
     भारता
    -0.06
    Thr
    -0.06
     Electricity
    -0.06
     services
    -0.06
    kirk
    -0.06
     verifying
    -0.06
     ದೂರ
    -0.06
    应该是
    -0.06
     காலநிலை
    -0.06
    POSITIVE LOGITS
     eficaz
    0.07
     один
    0.06
    Applic
    0.06
     применя
    0.06
     leurs
    0.06
     общий
    0.06
     गन्ना
    0.06
     および
    0.06
     tekan
    0.06
     alkalmaz
    0.06
    Activations Density 0.009%

    No Known Activations