© 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. 130358
    Prev
    Next
    INDEX
    Explanations

    locations, alcohol, alert

    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
     club
    -0.07
    club
    -0.06
     bulunmaktadır
    -0.06
     belum
    -0.06
     صنا
    -0.06
    模仿
    -0.06
     grubu
    -0.06
     klub
    -0.06
    indust
    -0.06
    時点で
    -0.06
    POSITIVE LOGITS
     going
    0.07
     संबोधित
    0.07
    问
    0.07
    Going
    0.06
    問
    0.06
    たと
    0.06
    さん
    0.06
     どう
    0.06
    اں
    0.06
    رفت
    0.05
    Activations Density 0.020%

    No Known Activations