© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130843
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by phrase

    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
     innovative
    -0.07
     আশ্চর্যজনক
    -0.06
    interno
    -0.06
     hardcore
    -0.06
     mesela
    -0.06
    kuat
    -0.06
    める
    -0.06
    бар
    -0.06
    분에
    -0.06
    ilgan
    -0.06
    POSITIVE LOGITS
     thì
    0.07
     should
    0.07
    全
    0.07
    ，
    0.06
    全是
    0.06
    一直是
    0.06
    就是
    0.06
    ,
    0.06
     solltest
    0.06
     должны
    0.06
    Activations Density 0.017%

    No Known Activations