© 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. 10-GEMMASCOPE-RES-131K
    7. 104075
    Prev
    Next
    INDEX
    Explanations

    sequential outcomes

    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_10/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
    </strong>
    -2.08
     belangrij
    -1.98
    𖥧
    -1.96
    amélioration
    -1.92
     duomen
    -1.89
     now
    -1.88
    沺
    -1.80
     nowadays
    -1.77
    なかな
    -1.77
     zijne
    -1.75
    POSITIVE LOGITS
    这
    2.31
    我们
    2.27
    鹇
    2.17
    ll
    2.13
     geladeira
    2.08
    b
    1.96
    傒
    1.88
    it
    1.88
    随着
    1.85
    The
    1.81
    Activations Density 0.029%

    No Known Activations