© 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. 120552
    Prev
    Next
    INDEX
    Explanations

    surgical approaches

    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
     pentru
    -0.06
     세포
    -0.06
    different
    -0.05
    Medical
    -0.05
    लीट
    -0.05
     regulatory
    -0.05
    δο
    -0.05
    Regulatory
    -0.05
    ষ্ণ
    -0.05
    Different
    -0.05
    POSITIVE LOGITS
     pairs
    0.07
     존재
    0.06
    采用
    0.06
     націона
    0.06
     tokens
    0.06
     bolts
    0.06
     существо
    0.06
    ាក់
    0.06
     عر
    0.06
     vouchers
    0.06
    Activations Density 0.022%

    No Known Activations