© 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. 119028
    Prev
    Next
    INDEX
    Explanations

    military and games

    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
     advisors
    -0.07
     advisers
    -0.07
    食
    -0.06
    Walking
    -0.06
     hypothalamus
    -0.06
     genome
    -0.06
    Kim
    -0.06
     Bethesda
    -0.06
    مون
    -0.06
     Kim
    -0.06
    POSITIVE LOGITS
     இன்னும்
    0.07
     воен
    0.06
     military
    0.06
    filler
    0.06
     kwiat
    0.06
     еще
    0.06
     patriotic
    0.06
     Cette
    0.06
    まだ
    0.06
     väldigt
    0.06
    Activations Density 0.008%

    No Known Activations