© 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. 128722
    Prev
    Next
    INDEX
    Explanations

    military ranks and roles

    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
     Thursday
    -0.07
    Thursday
    -0.06
     geniş
    -0.06
    他不
    -0.06
     jueves
    -0.06
     tonight
    -0.06
    今天
    -0.06
     broad
    -0.06
     Kenneth
    -0.06
     സ്
    -0.06
    POSITIVE LOGITS
     vacation
    0.06
     ouvido
    0.06
     states
    0.06
     Vacation
    0.06
     উচ্চ
    0.06
    ുകള
    0.06
    imerk
    0.06
     Midd
    0.05
     leveling
    0.05
     실제
    0.05
    Activations Density 0.007%

    No Known Activations