© 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. 117487
    Prev
    Next
    INDEX
    Explanations

    restriction followed by comma

    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
     nicht
    -0.10
     tidak
    -0.08
     não
    -0.08
    nicht
    -0.08
     ikke
    -0.07
     không
    -0.07
     realizar
    -0.07
     reducing
    -0.07
     trên
    -0.07
     egy
    -0.06
    POSITIVE LOGITS
     --------------
    0.06
    procedures
    0.06
     великолеп
    0.05
    _______
    0.05
     என்று
    0.05
    anine
    0.05
     dvě
    0.05
    訲
    0.05
    amed
    0.05
     چاہی
    0.05
    Activations Density 0.001%

    No Known Activations