© 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. 117439
    Prev
    Next
    INDEX
    Explanations

    command line execution and code execution

    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
     সমালোচনা
    -0.07
     Still
    -0.07
    涸
    -0.06
     empê
    -0.06
    Graduate
    -0.06
    INSTR
    -0.06
    江戸
    -0.06
     früheren
    -0.06
    召唤
    -0.06
    蠹
    -0.06
    POSITIVE LOGITS
     categorically
    0.06
     এসব
    0.05
     डेंटल
    0.05
     [
    0.05
     UINavigation
    0.05
    anced
    0.05
     mRNAs
    0.05
    拿出
    0.05
    hea
    0.05
    Juan
    0.05
    Activations Density 0.004%

    No Known Activations