© 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. 117145
    Prev
    Next
    INDEX
    Explanations

    travel caravan 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
     الحكم
    -0.08
     one
    -0.06
     শান্ত
    -0.06
     putative
    -0.06
    📻
    -0.06
     vinos
    -0.06
     seconds
    -0.06
    細かい
    -0.06
     rand
    -0.06
     забра
    -0.06
    POSITIVE LOGITS
     ضرورت
    0.07
     winter
    0.07
    Taxi
    0.06
    ئات
    0.06
    dala
    0.06
    abies
    0.06
    carrier
    0.06
     calendar
    0.06
     taxi
    0.05
    宴
    0.05
    Activations Density 0.008%

    No Known Activations