© 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. 116911
    Prev
    Next
    INDEX
    Explanations

    law firm names, individuals, and locations

    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
     tailored
    -0.08
     appli
    -0.07
     relaxed
    -0.06
     प्रैक्ट
    -0.06
    aplik
    -0.06
     परिभाषित
    -0.06
    他是
    -0.06
     executes
    -0.06
     asleep
    -0.06
     lectura
    -0.06
    POSITIVE LOGITS
     including
    0.07
    包括
    0.07
     inclusiv
    0.06
     consisting
    0.06
    :
    0.06
    B
    0.06
     जिसमें
    0.06
    ijan
    0.06
    their
    0.06
    完整
    0.06
    Activations Density 0.007%

    No Known Activations