© 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. 129400
    Prev
    Next
    INDEX
    Explanations

    helicopter and air

    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
    printer
    -0.07
     Racer
    -0.07
    国際
    -0.06
    Lunar
    -0.06
    racing
    -0.06
    Router
    -0.06
    Porsche
    -0.06
    Racing
    -0.06
     decarbon
    -0.06
     Router
    -0.06
    POSITIVE LOGITS
     removal
    0.06
     установ
    0.06
     คลิป
    0.06
     الفيديو
    0.06
    ダンス
    0.06
     Parent
    0.06
     установлено
    0.06
     कुटुंब
    0.06
    குடும்ப
    0.05
    дом
    0.05
    Activations Density 0.011%

    No Known Activations