© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 115826
    Prev
    Next
    INDEX
    Explanations

    local ip addresses

    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
    Negative Logits
    enni
    -0.06
    無法
    -0.06
    Internal
    -0.06
    INTERNAL
    -0.06
     forze
    -0.06
     empê
    -0.06
    자로
    -0.05
     nyil
    -0.05
    ποί
    -0.05
     keep
    -0.05
    POSITIVE LOGITS
     nhưng
    0.07
     અંત
    0.06
    illés
    0.06
     آتے
    0.06
     لكن
    0.06
    Լ
    0.06
     JButton
    0.06
     सकारात्मक
    0.05
     เช่น
    0.05
     لیکن
    0.05
    Activations Density 0.001%

    No Known Activations