© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129862
    Prev
    Next
    INDEX
    Explanations

    database

    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
     vouloir
    -0.07
     "",
    -0.06
    दो
    -0.06
    allclasses
    -0.06
    代
    -0.05
     next
    -0.05
    abad
    -0.05
     Monro
    -0.05
    ייס
    -0.05
     وكان
    -0.05
    POSITIVE LOGITS
     jsou
    0.07
     Cheyenne
    0.06
     Michelin
    0.06
     dissemination
    0.06
     भारतीयों
    0.06
     доступны
    0.06
     possono
    0.06
     могут
    0.06
     reflect
    0.06
    വി
    0.06
    Activations Density 0.035%

    No Known Activations