© 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. 129480
    Prev
    Next
    INDEX
    Explanations

    title, story, memoir, conflict

    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
    异
    -0.06
    .
    -0.06
     tohoto
    -0.06
    既
    -0.06
    very
    -0.06
    ange
    -0.06
     প্রেমের
    -0.05
    ifi
    -0.05
    Fetcher
    -0.05
    ↵
    -0.05
    POSITIVE LOGITS
    一個
    0.06
     can
    0.06
     Józ
    0.06
     pauses
    0.06
     주어진
    0.06
     vezet
    0.06
     đầu
    0.06
     unidos
    0.06
     trickle
    0.06
     pueden
    0.06
    Activations Density 0.029%

    No Known Activations