© 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. 118071
    Prev
    Next
    INDEX
    Explanations

    similar or equal comparison

    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
    riert
    -0.06
     sekä
    -0.06
    さらに
    -0.06
    sometimes
    -0.06
     neki
    -0.06
    ヽ
    -0.06
    These
    -0.06
     estão
    -0.06
    さら
    -0.06
     brasileira
    -0.05
    POSITIVE LOGITS
    నిక
    0.06
     or
    0.06
     be
    0.06
     similar
    0.06
     incr
    0.06
    検出
    0.06
     similaire
    0.06
    λεύ
    0.06
     displayed
    0.06
    检测
    0.06
    Activations Density 0.005%

    No Known Activations