© 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. 130905
    Prev
    Next
    INDEX
    Explanations

    -

    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
     all
    -0.07
    每一个
    -0.07
    所有的
    -0.07
     fiecare
    -0.07
     było
    -0.06
    当你
    -0.06
     모든
    -0.06
     courting
    -0.06
     wheelchairs
    -0.06
    每一個
    -0.06
    POSITIVE LOGITS
    ávan
    0.07
     अत
    0.06
    情報
    0.06
     정보
    0.06
     reales
    0.06
    लीज
    0.06
     reale
    0.06
    +'-
    0.06
     অনুরূপ
    0.06
     market
    0.06
    Activations Density 0.009%

    No Known Activations