© 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. 119675
    Prev
    Next
    INDEX
    Explanations

    even

    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
     лока
    -0.06
     :
    -0.06
    Ṣ
    -0.06
    にと
    -0.06
    ashvili
    -0.06
     dhat
    -0.06
    ↓↓
    -0.05
    幻想
    -0.05
    ３
    -0.05
     ಅವರು
    -0.05
    POSITIVE LOGITS
     disebut
    0.07
    <em>
    0.07
     შემდეგ
    0.06
    even
    0.06
    被称为
    0.06
     possibly
    0.06
    为什么
    0.06
    甚至
    0.06
    果然
    0.06
     даже
    0.06
    Activations Density 0.004%

    No Known Activations