© 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. 119883
    Prev
    Next
    INDEX
    Explanations

    cerebral, refused, rulings, based, invention

    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
    umlah
    -0.07
     امر
    -0.07
     आणि
    -0.06
    াৰ
    -0.06
     मेंबर
    -0.06
     additional
    -0.05
     रंगों
    -0.05
    াত্য
    -0.05
     दर्शकों
    -0.05
    iseach
    -0.05
    POSITIVE LOGITS
     এমনকি
    0.06
    லய
    0.06
     давно
    0.06
    ոտ
    0.06
     теор
    0.06
    ocken
    0.06
     klasik
    0.06
     meski
    0.06
    既に
    0.06
    स्पी
    0.06
    Activations Density 0.003%

    No Known Activations