© 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. 120023
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
     also
    -0.07
     yes
    -0.07
     damned
    -0.06
    하니
    -0.06
     degenerate
    -0.06
     even
    -0.06
     čak
    -0.06
     工具
    -0.05
     gardening
    -0.05
     lame
    -0.05
    POSITIVE LOGITS
     todos
    0.07
    這些
    0.07
     Todos
    0.06
    而在
    0.06
     Reporters
    0.06
     التي
    0.06
    label
    0.06
     paradigm
    0.06
     αυτές
    0.06
     பிரபல
    0.06
    Activations Density 0.010%

    No Known Activations