© 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. 118046
    Prev
    Next
    INDEX
    Explanations

    end tag closing brace

    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
    वानगी
    -0.06
     끝나
    -0.06
    㕲
    -0.06
     unfavorable
    -0.06
     closed
    -0.06
    height
    -0.06
    回到
    -0.06
     besuchte
    -0.06
    closed
    -0.06
     aperto
    -0.06
    POSITIVE LOGITS
     android
    0.07
     Android
    0.06
    提供了
    0.06
    ซึ่ง
    0.06
     oportunidad
    0.06
    给他
    0.06
     предостав
    0.06
    Quanto
    0.06
    给你
    0.06
    对此
    0.06
    Activations Density 0.002%

    No Known Activations