© 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. 128590
    Prev
    Next
    INDEX
    Explanations

    XML/markup tags, code, or list items

    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
     sẽ
    -0.07
     возь
    -0.07
     وسهلا
    -0.06
     будут
    -0.06
    だろう
    -0.06
    应该
    -0.06
     ought
    -0.06
    SPEAK
    -0.06
     saranno
    -0.05
    應該
    -0.05
    POSITIVE LOGITS
     मुंह
    0.06
     samt
    0.06
     típico
    0.06
     componentes
    0.06
     качестве
    0.06
    minimum
    0.06
    )^{*
    0.06
    ́ch
    0.06
    components
    0.06
     comprises
    0.06
    Activations Density 0.001%

    No Known Activations