© 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. 117542
    Prev
    Next
    INDEX
    Explanations

    `array` initialization and `values` attribute

    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
     Sp
    -0.06
    我
    -0.06
    世界的
    -0.05
    かと思います
    -0.05
     आकलन
    -0.05
     representar
    -0.05
    assessment
    -0.05
     scripture
    -0.05
     assessment
    -0.05
     historical
    -0.05
    POSITIVE LOGITS
     manière
    0.07
     także
    0.07
     також
    0.06
    也会
    0.06
     taip
    0.06
     meditative
    0.06
    also
    0.06
     andet
    0.06
     इट
    0.06
    رین
    0.06
    Activations Density 0.001%

    No Known Activations