© 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. 130287
    Prev
    Next
    INDEX
    Explanations

    NY Penal Law

    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
     gyak
    -0.06
     bezieht
    -0.06
    enb
    -0.06
    iebel
    -0.06
     anesthetic
    -0.06
     느껴
    -0.06
    NHL
    -0.06
     శాతం
    -0.06
    実感
    -0.05
     processo
    -0.05
    POSITIVE LOGITS
     but
    0.07
     для
    0.07
     கலங்கரை
    0.06
    Temporary
    0.06
    simple
    0.06
     simple
    0.06
     этого
    0.06
     цієї
    0.06
     quizás
    0.06
     giusto
    0.06
    Activations Density 0.002%

    No Known Activations