© 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. 130128
    Prev
    Next
    INDEX
    Explanations

    my followed by nouns

    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
    上的
    -0.07
    ել
    -0.06
     and
    -0.06
    全是
    -0.06
    之外
    -0.06
    Según
    -0.06
     però
    -0.06
     செய்து
    -0.05
    ）、
    -0.05
     ندار
    -0.05
    POSITIVE LOGITS
     evidently
    0.06
     останавли
    0.06
     possibly
    0.06
     shortly
    0.06
     двигателя
    0.06
     at
    0.06
     mismo
    0.06
     microbes
    0.06
     네트워크
    0.06
     kriv
    0.06
    Activations Density 0.017%

    No Known Activations