© 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. 129601
    Prev
    Next
    INDEX
    Explanations

    operating system installation and configuration

    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
     ﷺ
    -0.06
    😭
    -0.06
     Orchestra
    -0.06
    zsche
    -0.06
    ﷺ
    -0.06
     quibusdam
    -0.06
     அரங்க
    -0.06
     ‎
    -0.06
     orchestra
    -0.06
    Implement
    -0.06
    POSITIVE LOGITS
     telles
    0.07
     suitcases
    0.07
     gewüns
    0.06
     capture
    0.06
    :
    0.06
    Inside
    0.06
     snapshot
    0.06
     Inside
    0.06
     reputation
    0.06
     snapshots
    0.06
    Activations Density 0.012%

    No Known Activations