© 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. 128610
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific terms

    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
    数百
    -0.06
     similar
    -0.06
     подобных
    -0.06
    Several
    -0.06
     Several
    -0.06
     semelhantes
    -0.06
     wyja
    -0.05
    紓
    -0.05
    ではない
    -0.05
     Andrey
    -0.05
    POSITIVE LOGITS
    独立
    0.07
     ayrıca
    0.07
     additionally
    0.07
    
    0.07
    そもそも
    0.07
     그걸
    0.06
     eftersom
    0.06
     nämlich
    0.06
     السب
    0.06
    ibly
    0.06
    Activations Density 0.009%

    No Known Activations