© 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. 120141
    Prev
    Next
    INDEX
    Explanations

    military service

    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
     longstanding
    -0.07
     formerly
    -0.07
     renom
    -0.07
     आजही
    -0.06
     वर्णित
    -0.06
     eski
    -0.06
    habilit
    -0.06
     давно
    -0.06
     forgotten
    -0.06
     বর্তমানে
    -0.06
    POSITIVE LOGITS
     ಪ್ರಾರಂಭ
    0.06
    encode
    0.06
     partecipazione
    0.06
     zakoń
    0.06
     instrucción
    0.06
     unexpectedly
    0.06
     tipos
    0.06
     instructions
    0.05
    his
    0.05
    Instruction
    0.05
    Activations Density 0.002%

    No Known Activations