© 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. 129200
    Prev
    Next
    INDEX
    Explanations

    or, as, of, a

    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
    related
    -0.06
     David
    -0.06
    .
    -0.06
    这是
    -0.06
     بسته
    -0.05
    ).
    -0.05
    FY
    -0.05
    ബന്ധ
    -0.05
    ↵↵
    -0.05
     prije
    -0.05
    POSITIVE LOGITS
     IPv
    0.07
     afară
    0.07
     Javascript
    0.07
     डिफरेंट
    0.06
     दुस
    0.06
     inboard
    0.06
     all
    0.06
     indexing
    0.06
     sozialen
    0.06
     AFD
    0.06
    Activations Density 0.084%

    No Known Activations