© 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. 116739
    Prev
    Next
    INDEX
    Explanations

    place names and entities

    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
          
    -0.07
     mage
    -0.06
    想要
    -0.06
     thigh
    -0.06
     between
    -0.06
     during
    -0.06
           
    -0.06
     venga
    -0.06
     indi
    -0.06
     regional
    -0.06
    POSITIVE LOGITS
     situate
    0.07
    slightly
    0.07
     πρώτη
    0.06
     problemi
    0.06
    ட்டால்
    0.06
     primeira
    0.06
    刈
    0.06
     careful
    0.06
    ल्लभ
    0.06
     cuantos
    0.06
    Activations Density 0.001%

    No Known Activations