© 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. 119980
    Prev
    Next
    INDEX
    Explanations

    PATH, inherited, require

    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
    どんな
    -0.07
     outlay
    -0.06
    ensus
    -0.06
    टेज
    -0.06
     iaitu
    -0.06
     añadir
    -0.06
     Spence
    -0.06
    Although
    -0.06
    ಮಾಣ
    -0.06
    Keys
    -0.06
    POSITIVE LOGITS
    aaaaaaaa
    0.07
     drastically
    0.07
     accelerating
    0.06
     очеред
    0.06
    aaaa
    0.06
     efficiently
    0.06
     vigorously
    0.06
     proverb
    0.06
     restarted
    0.06
     संरक्षित
    0.06
    Activations Density 0.001%

    No Known Activations