© 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. 120255
    Prev
    Next
    INDEX
    Explanations

    geometric terms

    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
     स्थित
    -0.07
     соответственно
    -0.06
     clients
    -0.06
     Schwann
    -0.06
    欲しい
    -0.06
     oyn
    -0.06
     desired
    -0.06
     respectiv
    -0.06
     act
    -0.05
     respectively
    -0.05
    POSITIVE LOGITS
     valuable
    0.06
     என்
    0.06
     těchto
    0.06
     Verbre
    0.06
     સ્પ
    0.06
    TryParse
    0.06
     वित्त
    0.06
     mùa
    0.06
     geliştir
    0.06
     granic
    0.05
    Activations Density 0.027%

    No Known Activations