© 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. 117711
    Prev
    Next
    INDEX
    Explanations

    sudo commands with subsequent shell 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
     with
    -0.08
     at
    -0.07
                          
    -0.06
     from
    -0.06
                         
    -0.06
    instead
    -0.06
     when
    -0.06
     nessun
    -0.06
     without
    -0.06
    without
    -0.06
    POSITIVE LOGITS
     whopping
    0.06
    给你
    0.06
     genuinely
    0.06
     ಹಾಗೂ
    0.06
    Provides
    0.06
     comprens
    0.06
    Awesome
    0.06
    Abd
    0.06
     conceivably
    0.06
    Okay
    0.06
    Activations Density 0.006%

    No Known Activations