© 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. 117527
    Prev
    Next
    INDEX
    Explanations

    new pass

    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
     then
    -0.07
    そして
    -0.06
     And
    -0.06
     そして
    -0.06
     Это
    -0.06
     Then
    -0.06
     그리고
    -0.06
     hugely
    -0.06
     გამო
    -0.06
     however
    -0.06
    POSITIVE LOGITS
     ಎಂಬ
    0.07
    ním
    0.06
     बुध
    0.06
    是通过
    0.06
    仆
    0.06
    两条
    0.05
    都要
    0.05
     đựng
    0.05
     адміністра
    0.05
     interprets
    0.05
    Activations Density 0.001%

    No Known Activations