© 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. 129725
    Prev
    Next
    INDEX
    Explanations

    code imports and syntax

    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
    高い
    -0.06
    您的
    -0.06
    જ
    -0.06
    ਿਤ
    -0.05
    減少
    -0.05
    他们的
    -0.05
     감소
    -0.05
     meu
    -0.05
    あなたの
    -0.05
    חל
    -0.05
    POSITIVE LOGITS
     one
    0.07
     وتش
    0.07
    also
    0.07
    Also
    0.07
     also
    0.06
     toplant
    0.06
     też
    0.06
     Also
    0.06
     بوابة
    0.06
     גם
    0.06
    Activations Density 0.001%

    No Known Activations