© 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. 118815
    Prev
    Next
    INDEX
    Explanations

    textual descriptions of specific entities

    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
     hecha
    -0.06
     nered
    -0.06
    くれ
    -0.06
     অপারে
    -0.06
     comien
    -0.06
     ہونے
    -0.06
    どこ
    -0.06
     ඇත
    -0.06
     acclaimed
    -0.06
    いずれ
    -0.06
    POSITIVE LOGITS
     correctly
    0.07
     özelli
    0.06
     Takes
    0.06
     corrects
    0.06
     სწ
    0.06
     রবিবার
    0.06
    Takes
    0.06
     allows
    0.06
    reet
    0.06
    正确
    0.06
    Activations Density 0.063%

    No Known Activations