© 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. 117816
    Prev
    Next
    INDEX
    Explanations

    to end questions or statements

    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
    其他的
    -0.07
    目光
    -0.06
    ತೆಯ
    -0.06
     بقول
    -0.06
     Zudem
    -0.06
     Beneath
    -0.06
     theories
    -0.06
    canny
    -0.06
     realizada
    -0.06
     الأخرى
    -0.06
    POSITIVE LOGITS
     sciatica
    0.06
     adversity
    0.06
    🟣
    0.06
     difíciles
    0.05
     மாதிரி
    0.05
    ㅓ
    0.05
     पनि
    0.05
     people
    0.05
     confrontation
    0.05
     lst
    0.05
    Activations Density 0.015%

    No Known Activations