© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90584
    Prev
    Next
    INDEX
    Explanations

    terms starting definitions or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    املة
    -0.88
     dekat
    -0.88
     kuva
    -0.85
    形状
    -0.82
     Mě
    -0.82
     alko
    -0.81
     manquante
    -0.81
    nél
    -0.81
     TOPOLOGY
    -0.81
    矢量
    -0.80
    POSITIVE LOGITS
     рассматри
    0.90
    LElement
    0.84
    тин
    0.83
    ジオ
    0.77
    を加
    0.76
     Kentucky
    0.76
    <tr>
    0.76
    ൌ
    0.75
     хотелось
    0.75
    ртуаль
    0.75
    Activations Density 0.006%

    No Known Activations