© 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. 130014
    Prev
    Next
    INDEX
    Explanations

    numbers and statistical terms

    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
     Veterans
    -0.06
     milieux
    -0.06
     those
    -0.06
    ِينَ
    -0.06
     обнов
    -0.06
     FEST
    -0.06
    بعض
    -0.06
     AMERICAN
    -0.06
     Palace
    -0.06
     بعض
    -0.06
    POSITIVE LOGITS
    的一切
    0.06
     sufficient
    0.06
    prehensive
    0.06
    ,
    0.06
     comprehensive
    0.06
     drugo
    0.06
     terrible
    0.06
     igre
    0.06
     reicht
    0.06
    К
    0.06
    Activations Density 0.001%

    No Known Activations