© 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. 116472
    Prev
    Next
    INDEX
    Explanations

    ETSI/protocol/Enron/Erin/SATA

    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
     знают
    -0.07
     savent
    -0.06
     мира
    -0.06
    ."
    -0.06
    heat
    -0.06
    毕竟
    -0.06
     Loves
    -0.05
     ljubav
    -0.05
     known
    -0.05
    ".
    -0.05
    POSITIVE LOGITS
    緊急
    0.06
     महज
    0.06
    Restaurants
    0.06
     வேகமாக
    0.06
    🥖
    0.06
     OTHER
    0.06
     EMERGENCY
    0.06
     IMMEDI
    0.06
     fonctionne
    0.06
     다른
    0.06
    Activations Density 0.001%

    No Known Activations