© 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. 129771
    Prev
    Next
    INDEX
    Explanations

    breakfast items: eggs, cheese, toast

    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
     shrimps
    -0.06
     sehr
    -0.06
    แค่
    -0.06
     savun
    -0.06
     ऊंचाई
    -0.06
    休暇
    -0.06
    atan
    -0.06
    했고
    -0.06
     could
    -0.06
     sehingga
    -0.06
    POSITIVE LOGITS
     ७
    0.07
     没有
    0.06
    ２
    0.06
     third
    0.06
     ہمارے
    0.06
     ഹോ
    0.06
    ٨
    0.06
    ３
    0.06
     আমাদের
    0.06
     hỏi
    0.06
    Activations Density 0.007%

    No Known Activations