© 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. 118612
    Prev
    Next
    INDEX
    Explanations

    i'm statements

    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
    ছিল
    -0.07
     almeno
    -0.06
     aquela
    -0.06
    提供
    -0.06
    mming
    -0.06
    athon
    -0.05
    )
    -0.05
     Bagn
    -0.05
     genres
    -0.05
     trochu
    -0.05
    POSITIVE LOGITS
     ৷
    0.07
    マグ
    0.07
     zdecyd
    0.06
    是
    0.06
     그러나
    0.06
     отказа
    0.06
    。『
    0.06
     मुख्यतः
    0.06
    是大
    0.06
     ἀ
    0.06
    Activations Density 0.034%

    No Known Activations