© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117828
    Prev
    Next
    INDEX
    Explanations

    sign up, sign in, login, register, complete, restore

    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
     және
    -0.06
     विश्लेषण
    -0.06
     slideshow
    -0.06
    Analysis
    -0.06
     Analysis
    -0.05
    IND
    -0.05
     tehn
    -0.05
     chag
    -0.05
    measure
    -0.05
     আবারও
    -0.05
    POSITIVE LOGITS
     hund
    0.07
    同一个
    0.06
     měl
    0.06
     Last
    0.06
     uniquely
    0.06
    缩小
    0.06
     completos
    0.06
     максима
    0.06
    引入
    0.06
    Пол
    0.06
    Activations Density 0.006%

    No Known Activations