© 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. 119393
    Prev
    Next
    INDEX
    Explanations

    Supreme Court rulings

    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
    Histor
    -0.06
     myster
    -0.06
     namelijk
    -0.06
    र्जर
    -0.06
     किसका
    -0.06
     dessous
    -0.05
     Tradition
    -0.05
    NOUNC
    -0.05
     formalism
    -0.05
     messy
    -0.05
    POSITIVE LOGITS
     дополни
    0.07
     tablo
    0.06
    Such
    0.06
     этом
    0.06
    ૪
    0.06
     pamphlets
    0.06
    这类
    0.06
     SUCH
    0.06
     angling
    0.06
     scheming
    0.06
    Activations Density 0.006%

    No Known Activations