© 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. 129883
    Prev
    Next
    INDEX
    Explanations

    android attributes, xml tags, code keywords

    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
     মেধ
    -0.06
     authorized
    -0.06
     designated
    -0.06
     allowable
    -0.05
     igjen
    -0.05
    authorized
    -0.05
     entitlement
    -0.05
    its
    -0.05
     aforementioned
    -0.05
    POSITIVE LOGITS
     것으로
    0.07
     사회
    0.07
     От
    0.07
     which
    0.07
     usuário
    0.07
     vídeos
    0.07
     क्रिकेट
    0.07
    トマト
    0.07
     programas
    0.06
     用户
    0.06
    Activations Density 0.003%

    No Known Activations