© 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. 117623
    Prev
    Next
    INDEX
    Explanations

    wound and ulcer treatment

    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
    Its
    -0.08
     Its
    -0.08
     Shirts
    -0.07
     കൂടുതല്‍
    -0.06
     soweit
    -0.06
    Shirts
    -0.06
    These
    -0.06
    California
    -0.06
     dvou
    -0.06
    its
    -0.06
    POSITIVE LOGITS
    失败
    0.06
     faster
    0.06
    輝
    0.06
    reporting
    0.06
    يذ
    0.06
     unsuccessful
    0.05
     실패
    0.05
     ব্যর্থ
    0.05
     reported
    0.05
    failures
    0.05
    Activations Density 0.012%

    No Known Activations