© 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. 129249
    Prev
    Next
    INDEX
    Explanations

    direction or route

    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
     together
    -0.07
     совмести
    -0.07
     bersama
    -0.07
     चरणों
    -0.06
    setDate
    -0.06
     delicate
    -0.06
    အတူ
    -0.06
    픔
    -0.06
     zusammen
    -0.06
     accompany
    -0.06
    POSITIVE LOGITS
     wrong
    0.07
     방향
    0.07
    ผิด
    0.06
     incorrect
    0.06
    方向
    0.06
    wrong
    0.06
     trying
    0.06
    Wrong
    0.06
     Wrong
    0.06
    trying
    0.06
    Activations Density 0.012%

    No Known Activations