© 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. 118755
    Prev
    Next
    INDEX
    Explanations

    self-identified

    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
    CISE
    -0.06
    always
    -0.06
     stray
    -0.06
     झाल्या
    -0.06
    TCP
    -0.06
     inhomogeneous
    -0.06
    वंश
    -0.06
     hefty
    -0.06
     immer
    -0.06
    整个
    -0.06
    POSITIVE LOGITS
     autobi
    0.07
     аст
    0.06
     covert
    0.06
     unim
    0.06
     conceit
    0.06
     menggambarkan
    0.06
    ਦਾ
    0.06
    根据
    0.06
    根據
    0.06
     Browse
    0.06
    Activations Density 0.010%

    No Known Activations