© 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. 128793
    Prev
    Next
    INDEX
    Explanations

    Liebknecht, Muslim, SUP, ex

    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
    㢼
    -0.06
    бою
    -0.06
     government
    -0.06
     wouldn
    -0.06
     impressed
    -0.06
     वाणिज्य
    -0.05
    प्रधानमंत्री
    -0.05
     kullan
    -0.05
    นี่
    -0.05
    ці
    -0.05
    POSITIVE LOGITS
     যখন
    0.07
     disagreements
    0.07
     Editions
    0.06
     unten
    0.06
     disagreement
    0.06
    馇
    0.06
    违反
    0.06
     βασ
    0.06
    trecht
    0.06
     ortam
    0.06
    Activations Density 0.018%

    No Known Activations