© 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. 119082
    Prev
    Next
    INDEX
    Explanations

    HTML tags or annotations

    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
     অবধি
    -0.06
    oxins
    -0.06
     is
    -0.06
    她的
    -0.06
    :
    -0.06
    changes
    -0.06
     на
    -0.06
    Я
    -0.06
     size
    -0.06
    까지
    -0.06
    POSITIVE LOGITS
    ᴄ
    0.07
     avoiding
    0.06
     showing
    0.06
     dyspe
    0.06
     clearly
    0.06
    𝑓
    0.06
    kde
    0.06
     indigestion
    0.06
    はず
    0.06
    栻
    0.06
    Activations Density 0.002%

    No Known Activations