© 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. 128607
    Prev
    Next
    INDEX
    Explanations

    trying/attempting to

    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
     berisi
    -0.06
    やや
    -0.06
     Между
    -0.06
     jurul
    -0.06
     चपेट
    -0.06
     sekitar
    -0.06
     조금
    -0.06
     ඉක්
    -0.06
    waitTime
    -0.06
     чуть
    -0.06
    POSITIVE LOGITS
    ou
    0.06
    ធាតុ
    0.06
     problems
    0.06
     previously
    0.06
     reduces
    0.06
     بالفعل
    0.06
     ما
    0.05
     خاص
    0.05
    <b>
    0.05
     пенсии
    0.05
    Activations Density 0.008%

    No Known Activations