© 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. 130081
    Prev
    Next
    INDEX
    Explanations

    network shares

    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
    sca
    -0.06
     Irak
    -0.06
     здание
    -0.06
    irio
    -0.05
     metadata
    -0.05
     preservation
    -0.05
     ща
    -0.05
     Exponential
    -0.05
     gerek
    -0.05
    Saf
    -0.05
    POSITIVE LOGITS
    开放
    0.07
    經濟
    0.07
     відкри
    0.06
     économique
    0.06
     southern
    0.06
     Жен
    0.06
    હે
    0.06
    เปิด
    0.06
    開放
    0.06
     swimmers
    0.06
    Activations Density 0.016%

    No Known Activations