© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117896
    Prev
    Next
    INDEX
    Explanations

    system calls or sys commands

    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
     offline
    -0.06
     takeaway
    -0.06
     நிறைவே
    -0.06
     Mala
    -0.06
     significa
    -0.05
     eradic
    -0.05
     issus
    -0.05
    粝
    -0.05
    ພວກເຮົາ
    -0.05
     ਲੈ
    -0.05
    POSITIVE LOGITS
     ধারে
    0.06
    posterior
    0.06
     admiring
    0.06
     શબ્
    0.06
    」、「
    0.06
     stiffness
    0.06
    তীশ
    0.06
    player
    0.06
     antes
    0.06
     rever
    0.06
    Activations Density 0.001%

    No Known Activations