© 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. 117271
    Prev
    Next
    INDEX
    Explanations

    introduction or section headers

    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
     sculpted
    -0.06
    ohia
    -0.06
     specific
    -0.06
     फील्ड
    -0.06
    特定的
    -0.06
     بالنسب
    -0.06
     específicos
    -0.06
    oris
    -0.06
     ಕುಟ
    -0.06
     jeweiligen
    -0.06
    POSITIVE LOGITS
     terdapat
    0.06
    Indicators
    0.06
    行人
    0.06
    indicators
    0.05
    大哥
    0.05
     অস্তিত্ব
    0.05
    ່
    0.05
     আপাত
    0.05
    管制
    0.05
     secur
    0.05
    Activations Density 0.004%

    No Known Activations