© 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. 130084
    Prev
    Next
    INDEX
    Explanations

    album, debut, official, results, term, member, League

    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
     accompaniment
    -0.06
    MANY
    -0.06
     quay
    -0.06
     ôn
    -0.06
    ണു
    -0.06
     még
    -0.05
     پانی
    -0.05
    中小
    -0.05
    <0xAD>
    -0.05
     comforting
    -0.05
    POSITIVE LOGITS
     Consecutive
    0.06
    正規品
    0.06
     Somebody
    0.06
    Ahora
    0.06
     ন্যাশনাল
    0.06
     maq
    0.06
     الأول
    0.05
     הראשון
    0.05
     اید
    0.05
     इसको
    0.05
    Activations Density 0.090%

    No Known Activations