© 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. 118181
    Prev
    Next
    INDEX
    Explanations

    function definitions

    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
    そして
    -0.07
     그리고
    -0.07
     rossa
    -0.06
     กับ
    -0.06
     Rebels
    -0.06
     הרבה
    -0.06
    ⁺
    -0.06
     そして
    -0.06
    েরি
    -0.06
     ஈடுபட்டு
    -0.06
    POSITIVE LOGITS
    Odd
    0.06
     desenhos
    0.06
     popular
    0.06
     its
    0.06
     kere
    0.06
    abilität
    0.06
     AD
    0.06
     foundations
    0.06
    Ley
    0.06
     at
    0.05
    Activations Density 0.001%

    No Known Activations