© 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. 119895
    Prev
    Next
    INDEX
    Explanations

    URLs or path separators after certain words

    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
     podob
    -0.07
     подобные
    -0.07
     создании
    -0.07
     이곳
    -0.07
     Depois
    -0.07
    🤑
    -0.07
     testis
    -0.06
     подобных
    -0.06
    kitchen
    -0.06
    😲
    -0.06
    POSITIVE LOGITS
    ↵
    0.06
     will
    0.06
    Е
    0.06
    เดียว
    0.05
     merely
    0.05
     Treating
    0.05
     alone
    0.05
     from
    0.05
     challenges
    0.05
     introduces
    0.05
    Activations Density 0.001%

    No Known Activations