© 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. 117786
    Prev
    Next
    INDEX
    Explanations

    where clause

    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
    برای
    -0.07
     وقتی
    -0.07
    設定
    -0.07
     последствия
    -0.07
     letzten
    -0.07
     dietary
    -0.06
     seperti
    -0.06
     Dietary
    -0.06
     threatened
    -0.06
    隣
    -0.06
    POSITIVE LOGITS
     hugely
    0.07
     which
    0.06
     known
    0.06
     জন্মগ্রহণ
    0.06
     immense
    0.06
    ǧ
    0.06
     dashed
    0.06
    numeric
    0.06
     Mar
    0.06
     isValid
    0.06
    Activations Density 0.008%

    No Known Activations