© 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. 128934
    Prev
    Next
    INDEX
    Explanations

    ATM ( , , , long, captain, doctype )

    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
     sebelum
    -0.07
    नाटक
    -0.06
     sociologist
    -0.06
     similarities
    -0.06
    Election
    -0.06
     BEFORE
    -0.06
     températures
    -0.06
     Pharmaceutical
    -0.06
     JOHN
    -0.06
     sql
    -0.06
    POSITIVE LOGITS
     numerous
    0.06
     pursuing
    0.06
    ंवर
    0.05
    㑬
    0.05
    จร
    0.05
     ).
    0.05
    );
    0.05
     а
    0.05
     Habana
    0.05
     diversity
    0.05
    Activations Density 0.001%

    No Known Activations