© 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. 129919
    Prev
    Next
    INDEX
    Explanations

    school names and types

    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
     eliminated
    -0.06
     افزایش
    -0.06
     drumming
    -0.06
     Mitglieder
    -0.06
    格局
    -0.06
    柿
    -0.06
     없습니다
    -0.06
     Besuch
    -0.06
     শার
    -0.06
     framing
    -0.05
    POSITIVE LOGITS
     त्वरित
    0.07
    いたり
    0.07
     pathway
    0.06
     conduct
    0.06
    Multiple
    0.06
    短短
    0.06
     aims
    0.06
     hızlı
    0.06
     or
    0.06
     સાર
    0.06
    Activations Density 0.003%

    No Known Activations