© 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. 119876
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and common medical terms

    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
     드릴
    -0.06
     Vorteil
    -0.06
    rica
    -0.06
     campaigners
    -0.06
    Disable
    -0.06
    numberOfRecords
    -0.06
     ranges
    -0.06
     identifications
    -0.06
     disable
    -0.06
     مثل
    -0.06
    POSITIVE LOGITS
    ią
    0.06
     legacy
    0.06
    如果你
    0.06
     was
    0.06
    낸
    0.06
     and
    0.05
     kari
    0.05
    看到
    0.05
     был
    0.05
     kult
    0.05
    Activations Density 0.006%

    No Known Activations