© 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. 127243
    Prev
    Next
    INDEX
    Explanations

    test case for bugs and files

    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
    }
    -2.11
     trovano
    -2.05
     The
    -1.78
    もありますが
    -1.61
    nummer
    -1.60
     =
    -1.58
    もありました
    -1.58
     praktische
    -1.57
     historische
    -1.56
    隂
    -1.55
    POSITIVE LOGITS
    one
    2.09
    䊏
    1.96
    𓋼
    1.88
    BagLayout
    1.81
    ፱
    1.80
     that
    1.80
    刧
    1.73
    .”
    1.71
     españolas
    1.69
    他の
    1.68
    Activations Density 0.009%

    No Known Activations