© 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. 129872
    Prev
    Next
    INDEX
    Explanations

    cruise ship embarkation

    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
     estaba
    -0.07
    囔
    -0.07
    Ви
    -0.07
     মনীষ
    -0.07
     커피
    -0.07
    যখন
    -0.06
     وہاں
    -0.06
    がありました
    -0.06
     डबल
    -0.06
    ashington
    -0.06
    POSITIVE LOGITS
    unik
    0.06
    ∨
    0.05
     바탕
    0.05
     revealing
    0.05
    <em>
    0.05
     disclosing
    0.05
    纯
    0.05
     their
    0.05
     describing
    0.05
    老
    0.05
    Activations Density 0.010%

    No Known Activations