© 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. 129915
    Prev
    Next
    INDEX
    Explanations

    world leader

    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
     трёх
    -0.07
     soutenir
    -0.07
     سه
    -0.06
    ℍ
    -0.06
     fullName
    -0.06
     трех
    -0.06
     doping
    -0.06
    ロック
    -0.06
     четырех
    -0.06
    Colour
    -0.06
    POSITIVE LOGITS
    㭜
    0.06
     yoktur
    0.06
     RCP
    0.05
    aternal
    0.05
     talvez
    0.05
     قریب
    0.05
     కంటే
    0.05
     बगैर
    0.05
    人和
    0.05
     perhaps
    0.05
    Activations Density 0.007%

    No Known Activations