© 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. 130577
    Prev
    Next
    INDEX
    Explanations

    following commands

    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
     disney
    -0.07
    Disney
    -0.06
    ynge
    -0.06
     betrayed
    -0.06
    zoo
    -0.06
     accessToken
    -0.06
    reason
    -0.06
     Rahmen
    -0.06
     login
    -0.06
    拿着
    -0.06
    POSITIVE LOGITS
     sẽ
    0.06
     compiling
    0.06
     reputable
    0.06
     försö
    0.06
     partir
    0.06
    following
    0.06
    จะ
    0.06
     succeeding
    0.06
     последу
    0.06
     پہا
    0.06
    Activations Density 0.002%

    No Known Activations