© 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. 117226
    Prev
    Next
    INDEX
    Explanations

    metal industries

    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
     keep
    -0.06
    兼
    -0.06
     ausschließlich
    -0.06
    አ
    -0.06
    ishop
    -0.06
    になると
    -0.06
     বাতাসে
    -0.06
    保持
    -0.06
     relatively
    -0.06
    टो
    -0.05
    POSITIVE LOGITS
     discursive
    0.07
     leftmost
    0.06
     dyspe
    0.06
     предупре
    0.06
     Donation
    0.06
    ⚔
    0.06
     Çocuk
    0.06
     datetime
    0.06
     لوی
    0.06
     ফেসবুক
    0.06
    Activations Density 0.010%

    No Known Activations