© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130856
    Prev
    Next
    INDEX
    Explanations

    numbers or specific 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
     друже
    -0.06
     sahabat
    -0.06
    Designed
    -0.06
     bicarbonate
    -0.05
     except
    -0.05
     attachments
    -0.05
     metaphorical
    -0.05
    Historically
    -0.05
     Designed
    -0.05
     Gand
    -0.05
    POSITIVE LOGITS
     two
    0.07
     zwei
    0.07
     δύο
    0.06
     două
    0.06
    兩個
    0.06
    MOVEMENT
    0.06
     gerekir
    0.06
    俩
    0.06
    两个
    0.06
     stolen
    0.06
    Activations Density 0.002%

    No Known Activations