© 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. 129476
    Prev
    Next
    INDEX
    Explanations

    used to

    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
    従来
    -0.07
    既存
    -0.06
    以往
    -0.06
     vorige
    -0.06
     first
    -0.06
     yesterday
    -0.06
     traditionally
    -0.06
    線性
    -0.06
    之前
    -0.06
    ปกติ
    -0.06
    POSITIVE LOGITS
     از
    0.07
     all
    0.07
     từ
    0.07
     và
    0.07
     póź
    0.06
     mỗi
    0.06
    从
    0.06
     moderno
    0.06
    后的
    0.06
     все
    0.06
    Activations Density 0.011%

    No Known Activations