© 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. 117179
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     không
    -0.09
     erhalten
    -0.08
     received
    -0.08
     pentru
    -0.07
    Unfortunately
    -0.07
     제외
    -0.07
     hanya
    -0.07
     nicht
    -0.07
     추가
    -0.07
    không
    -0.07
    POSITIVE LOGITS
     règ
    0.06
     such
    0.06
     useNavigate
    0.06
    ￥
    0.06
    这一切
    0.05
    ¥
    0.05
    ầ
    0.05
    such
    0.05
     transporting
    0.05
    詳しくは
    0.05
    Activations Density 0.013%

    No Known Activations