© 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. 129879
    Prev
    Next
    INDEX
    Explanations

    dates and names

    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
    ↵
    -0.12
     よ
    -0.06
     după
    -0.06
     Bukan
    -0.06
     செயற்க
    -0.06
    不是
    -0.06
    ມື
    -0.06
     amelyek
    -0.05
     after
    -0.05
    weh
    -0.05
    POSITIVE LOGITS
     like
    0.07
     history
    0.06
     مثل
    0.06
     putea
    0.06
     полный
    0.06
    带动
    0.06
     deci
    0.06
    구매
    0.06
     దీ
    0.05
     excurs
    0.05
    Activations Density 0.003%

    No Known Activations