© 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. 116868
    Prev
    Next
    INDEX
    Explanations

    years, events, or numbers

    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
     the
    -0.08
    真正的
    -0.06
    -
    -0.06
     methodology
    -0.05
     trotz
    -0.05
     вважа
    -0.05
     오히려
    -0.05
     conna
    -0.05
     hingegen
    -0.05
     random
    -0.05
    POSITIVE LOGITS
    एलबी
    0.06
     중에서
    0.06
     WHICH
    0.06
    हुल
    0.06
     क्योंकि
    0.06
     různých
    0.06
    經濟
    0.06
    dry
    0.06
    들이
    0.06
    நீ
    0.06
    Activations Density 0.036%

    No Known Activations