© 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. 117604
    Prev
    Next
    INDEX
    Explanations

    transmitted by, spread by, transmission routes

    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
     использу
    -0.07
    Adress
    -0.07
     complicating
    -0.06
     النرويج
    -0.06
     Sebab
    -0.06
     suisse
    -0.06
     illnesses
    -0.06
    城県
    -0.06
    BankAccount
    -0.06
     adress
    -0.06
    POSITIVE LOGITS
    text
    0.05
    വ
    0.05
     gén
    0.05
     bet
    0.05
    agher
    0.05
    合计
    0.05
    index
    0.05
    asil
    0.05
    ကာ
    0.05
    CAO
    0.05
    Activations Density 0.011%

    No Known Activations