© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 129716
    Prev
    Next
    INDEX
    Explanations

    name of a thing or place

    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
     பெரும்பாலான
    -0.07
     பெரும்பாலும்
    -0.07
     automatique
    -0.06
     větš
    -0.06
     대부분
    -0.06
    ͎
    -0.06
    ';...
    -0.06
     flour
    -0.06
     اغلب
    -0.06
     gerar
    -0.06
    POSITIVE LOGITS
     different
    0.06
     pattes
    0.06
     time
    0.06
    name
    0.06
     κάπο
    0.05
    異なる
    0.05
     నిర్మా
    0.05
     these
    0.05
    いわ
    0.05
     important
    0.05
    Activations Density 0.088%

    No Known Activations