© 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. 130170
    Prev
    Next
    INDEX
    Explanations

    continued

    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
     whatnot
    -0.06
     নাব
    -0.06
    riterien
    -0.06
    ಲೆಯ
    -0.06
     पोखर
    -0.06
     wisely
    -0.06
    最適
    -0.06
    我的
    -0.06
     उत्तरा
    -0.06
     சமய
    -0.05
    POSITIVE LOGITS
    继续
    0.07
     продовжу
    0.07
    繼續
    0.07
     pokrač
    0.06
     continued
    0.06
     continuare
    0.06
     continue
    0.06
     повы
    0.06
     продолжа
    0.06
     继续
    0.06
    Activations Density 0.010%

    No Known Activations