© 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. 119153
    Prev
    Next
    INDEX
    Explanations

    layout; stimulation; disordered

    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
    ادث
    -0.06
     پڑے
    -0.06
    transaction
    -0.05
     happened
    -0.05
     ieder
    -0.05
     daran
    -0.05
    epat
    -0.05
     daugiau
    -0.05
     sekali
    -0.05
    сову
    -0.05
    POSITIVE LOGITS
    ামূলক
    0.06
     två
    0.06
     उत्पादों
    0.06
     genuinely
    0.06
     iki
    0.06
     दोस्ती
    0.06
     እስከ
    0.06
     δύο
    0.06
    常规
    0.06
    _{\
    0.06
    Activations Density 0.002%

    No Known Activations