© 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. 130381
    Prev
    Next
    INDEX
    Explanations

    community or neighborhood

    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
    стая
    -0.06
     કંઈ
    -0.06
     referred
    -0.05
    👢
    -0.05
     प्रमाणपत्र
    -0.05
     Referred
    -0.05
     來
    -0.05
     acest
    -0.05
     લગભગ
    -0.05
    gano
    -0.05
    POSITIVE LOGITS
     gemeins
    0.06
     طبي
    0.06
     one
    0.06
    community
    0.06
     terão
    0.06
     community
    0.06
     tendrán
    0.06
    社區
    0.06
     tendrá
    0.06
     شاهد
    0.05
    Activations Density 0.011%

    No Known Activations