© 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. 120622
    Prev
    Next
    INDEX
    Explanations

    according to

    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
    !
    -0.06
     scant
    -0.06
     (!
    -0.05
    +
    -0.05
     कंडी
    -0.05
     bột
    -0.05
     nennt
    -0.05
    fla
    -0.05
    list
    -0.05
     enterprising
    -0.05
    POSITIVE LOGITS
     corrupt
    0.07
     Corruption
    0.07
    又
    0.07
    
    0.07
     moje
    0.06
    持續
    0.06
     আবারও
    0.06
    持续
    0.06
    Corruption
    0.06
    समय
    0.06
    Activations Density 0.026%

    No Known Activations