© 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. 130538
    Prev
    Next
    INDEX
    Explanations

    stealing, stolen, theft, burglary, looting

    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
    pur
    -0.06
     navigational
    -0.06
    แต่ละ
    -0.06
    ாண்ட
    -0.06
     trouv
    -0.06
     மாசு
    -0.05
     estudo
    -0.05
     పంచ
    -0.05
     searchText
    -0.05
    business
    -0.05
    POSITIVE LOGITS
    Final
    0.06
    ........
    0.06
     frequently
    0.06
    FINAL
    0.06
     final
    0.06
     Final
    0.06
    Lista
    0.06
     대한민국
    0.06
    final
    0.06
     FINAL
    0.06
    Activations Density 0.008%

    No Known Activations