© 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. 118045
    Prev
    Next
    INDEX
    Explanations

    military actions and events

    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
     якобы
    -0.07
     former
    -0.06
     presumably
    -0.05
     Hopefully
    -0.05
    /***
    -0.05
     Presumably
    -0.05
     ব্যাঙ্ক
    -0.05
     ways
    -0.05
     क्षमता
    -0.05
     them
    -0.05
    POSITIVE LOGITS
     cornerstone
    0.07
     dadurch
    0.07
    putable
    0.07
     complet
    0.06
    рович
    0.06
     approving
    0.06
     नेत
    0.06
    安慰
    0.06
    ષ્ટ
    0.06
    istently
    0.06
    Activations Density 0.006%

    No Known Activations