© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119253
    Prev
    Next
    INDEX
    Explanations

    programming code output statements

    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
    FirstName
    -0.06
    NAME
    -0.06
     بذلك
    -0.06
    第一個
    -0.06
     erstes
    -0.06
    第一个
    -0.06
     rezultat
    -0.05
    쪽
    -0.05
     সকলে
    -0.05
     eredmény
    -0.05
    POSITIVE LOGITS
     vodu
    0.06
     замени
    0.06
    쏟
    0.06
     Featuring
    0.06
     will
    0.06
     ausgestattet
    0.06
    ផ្តល់
    0.05
    Also
    0.05
    ἂ
    0.05
     Also
    0.05
    Activations Density 0.001%

    No Known Activations