© 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. 129867
    Prev
    Next
    INDEX
    Explanations

    writing messages or communication

    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
     теорети
    -0.06
    遛
    -0.06
     (
    -0.06
     விளக்க
    -0.06
     theoretical
    -0.05
     公式
    -0.05
    SourceIP
    -0.05
     set
    -0.05
     prens
    -0.05
     কিন্তু
    -0.05
    POSITIVE LOGITS
    स्क
    0.07
    Regardless
    0.07
     handwriting
    0.07
    Message
    0.06
     Messages
    0.06
     messages
    0.06
     मैसेज
    0.06
    Before
    0.06
    regel
    0.06
    我想
    0.06
    Activations Density 0.009%

    No Known Activations