© 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. 129548
    Prev
    Next
    INDEX
    Explanations

    limit per person or item

    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
     capacity
    -0.06
     declines
    -0.06
     capacité
    -0.06
     capacidade
    -0.06
     Capacity
    -0.06
     legally
    -0.06
    capacity
    -0.06
     হাউস
    -0.06
     более
    -0.06
     หมด
    -0.06
    POSITIVE LOGITS
     construcción
    0.07
    幫助
    0.06
    ຜະລ
    0.06
     proz
    0.06
     võib
    0.06
     afectan
    0.06
     ONE
    0.06
     location
    0.06
    遲
    0.06
     reconnaître
    0.06
    Activations Density 0.015%

    No Known Activations