© 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. 130382
    Prev
    Next
    INDEX
    Explanations

    personal opinions and 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
     expérience
    -0.06
     beserta
    -0.06
    他們
    -0.06
     чаще
    -0.06
     meestal
    -0.06
    他们
    -0.06
     साथ
    -0.06
    等待
    -0.06
     pengalaman
    -0.06
     junto
    -0.06
    POSITIVE LOGITS
     during
    0.07
     again
    0.06
     특히
    0.06
     特に
    0.06
     should
    0.06
     moved
    0.06
    imura
    0.05
     caused
    0.05
     several
    0.05
     (
    0.05
    Activations Density 0.002%

    No Known Activations