© 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. 117084
    Prev
    Next
    INDEX
    Explanations

    US state abbreviations

    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
     ......
    -0.06
    也
    -0.06
     ហើយ
    -0.06
     Acoustics
    -0.06
    皁
    -0.06
     escapes
    -0.06
     თან
    -0.05
     Nähe
    -0.05
     Expedition
    -0.05
     Finds
    -0.05
    POSITIVE LOGITS
     ৫৭
    0.07
    varphi
    0.07
    অপহরণ
    0.06
     بسیاری
    0.06
     اغلب
    0.06
     maupun
    0.06
    KS
    0.06
    あらゆる
    0.06
    不少
    0.06
     સમગ્ર
    0.06
    Activations Density 0.003%

    No Known Activations