© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118888
    Prev
    Next
    INDEX
    Explanations

    Proper names of people and pets

    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
     dovrebbe
    -0.06
     უნდა
    -0.06
     उन्हीं
    -0.06
     অর্থাৎ
    -0.06
     trebuie
    -0.06
     mythical
    -0.06
     goods
    -0.06
     devemos
    -0.05
     bisogna
    -0.05
     باید
    -0.05
    POSITIVE LOGITS
     geeft
    0.06
     बघ
    0.06
    부분
    0.06
    immediately
    0.06
    感じで
    0.06
     কখনই
    0.06
     spreads
    0.06
     ที
    0.06
     politique
    0.06
    itul
    0.06
    Activations Density 0.012%

    No Known Activations