© 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. 118425
    Prev
    Next
    INDEX
    Explanations

    "this case"

    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
     উপনিবেশ
    -0.06
     अखबार
    -0.06
     mejor
    -0.06
     pareil
    -0.06
     unless
    -0.06
    用户名
    -0.06
     עד
    -0.06
     مع
    -0.06
     તમારા
    -0.06
     +
    -0.06
    POSITIVE LOGITS
     حقیقی
    0.06
     several
    0.06
     خفی
    0.06
     vrai
    0.06
     erroneous
    0.06
    ღვ
    0.06
    
    0.06
    }\|^
    0.06
     prawdzi
    0.06
    に対し
    0.06
    Activations Density 0.061%

    No Known Activations