© 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. 119250
    Prev
    Next
    INDEX
    Explanations

    `.display` or `SESSION[`, or `<li`

    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
     objetivo
    -0.07
     রাখিয়া
    -0.07
     различные
    -0.07
    这是一个
    -0.07
     Kish
    -0.07
    なかった
    -0.07
     ofta
    -0.07
     большую
    -0.06
     μεγάλη
    -0.06
     jedną
    -0.06
    POSITIVE LOGITS
     ſ
    0.06
    Get
    0.05
     data
    0.05
    At
    0.05
     zau
    0.05
     />
    0.05
    control
    0.05
     get
    0.05
    data
    0.05
     ге
    0.05
    Activations Density 0.013%

    No Known Activations