© 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. 119490
    Prev
    Next
    INDEX
    Explanations

    java import statements

    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
    zzel
    -0.06
    Dn
    -0.06
    nocześnie
    -0.06
     envolv
    -0.06
    增加
    -0.06
     Zusätzlich
    -0.06
     Cez
    -0.05
    swith
    -0.05
     Related
    -0.05
    cter
    -0.05
    POSITIVE LOGITS
    它們
    0.07
     birt
    0.07
     would
    0.06
    它们
    0.06
     fourth
    0.06
     innego
    0.06
     halibut
    0.06
     ช่วย
    0.06
     birth
    0.06
     offrent
    0.06
    Activations Density 0.005%

    No Known Activations