© 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. 119528
    Prev
    Next
    INDEX
    Explanations

    Olivia Musgrave

    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
     ■
    -0.06
    ■
    -0.06
     an
    -0.06
     Also
    -0.06
     Question
    -0.06
    จำเป็น
    -0.06
     هستند
    -0.05
    Also
    -0.05
    ផ្ស
    -0.05
     են
    -0.05
    POSITIVE LOGITS
     현재
    0.08
     ikke
    0.07
     currently
    0.07
     tidak
    0.07
     attualmente
    0.07
    currently
    0.07
     actuellement
    0.06
     actualmente
    0.06
     teor
    0.06
     hegemony
    0.06
    Activations Density 0.002%

    No Known Activations