© 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. 129393
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by new clause

    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
     „
    -0.07
     ALSO
    -0.06
     definitely
    -0.06
     methanol
    -0.06
     puzzling
    -0.06
     wacky
    -0.06
     startling
    -0.06
            
    -0.06
    其他
    -0.06
    POSITIVE LOGITS
     oder
    0.07
     does
    0.06
    ʸ
    0.06
    এসসি
    0.06
     or
    0.06
    ;;
    0.06
    Able
    0.06
     doesn
    0.06
    是可以
    0.06
     ಒಬ್ಬ
    0.06
    Activations Density 0.007%

    No Known Activations