© 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. 120428
    Prev
    Next
    INDEX
    Explanations

    quantum physics and sexuality

    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
    跟大家
    -0.06
    гиз
    -0.06
     ব্যাপারে
    -0.06
     definitiva
    -0.06
    that
    -0.06
     restantes
    -0.06
    planned
    -0.06
    清晰
    -0.06
    推出的
    -0.06
    ister
    -0.06
    POSITIVE LOGITS
    がありました
    0.06
     demonstrates
    0.06
     watersheds
    0.06
    Supported
    0.06
     swayed
    0.06
     uncovering
    0.06
     spurred
    0.06
    supported
    0.06
     significantly
    0.06
     SUPPORT
    0.06
    Activations Density 0.012%

    No Known Activations