© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116533
    Prev
    Next
    INDEX
    Explanations

    free flap

    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
     исклю
    -0.07
     practice
    -0.07
     occurrences
    -0.06
     ocorr
    -0.06
     Next
    -0.06
     Texas
    -0.06
    ตรวจ
    -0.06
     উভ
    -0.06
     ώστε
    -0.06
     exclu
    -0.06
    POSITIVE LOGITS
     துணை
    0.08
     verbinden
    0.07
     versatility
    0.06
    ulfill
    0.06
    可以
    0.06
     flexibility
    0.06
     desplaz
    0.06
     ಸಹಾಯ
    0.06
     benefícios
    0.06
    ？
    0.06
    Activations Density 0.022%

    No Known Activations