© 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. 120553
    Prev
    Next
    INDEX
    Explanations

    days of the week and common nouns

    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
     أثناء
    -0.06
     macho
    -0.06
     Schwarz
    -0.06
    getRed
    -0.06
     obtains
    -0.05
    ثناء
    -0.05
     می‌تواند
    -0.05
     during
    -0.05
    Schwarz
    -0.05
    raag
    -0.05
    POSITIVE LOGITS
    asjonen
    0.06
     departe
    0.06
     memorable
    0.06
    而不是
    0.06
    ?>
    0.06
    然后
    0.06
     побе
    0.06
     assicur
    0.06
    所以
    0.06
     тот
    0.06
    Activations Density 0.001%

    No Known Activations