© 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. 117726
    Prev
    Next
    INDEX
    Explanations

    math and chemistry subjects

    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
     ilk
    -0.06
     أول
    -0.05
    に移
    -0.05
    නේ
    -0.05
     ভারসাম্য
    -0.05
    ใ
    -0.05
     Honours
    -0.05
     eerste
    -0.05
     rather
    -0.05
    ological
    -0.05
    POSITIVE LOGITS
     yaptı
    0.07
     अलग
    0.07
    Atual
    0.07
    ünk
    0.07
     người
    0.06
     aktual
    0.06
     மிசோ
    0.06
     사람
    0.06
     getCurrent
    0.06
    glich
    0.06
    Activations Density 0.005%

    No Known Activations