© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10672
    Prev
    Next
    INDEX
    Explanations

    phrases starting sentences or clauses

    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
     so
    -1.66
     there
    -1.66
     There
    -1.56
     An
    -1.54
    𝗜
    -1.52
     a
    -1.49
     on
    -1.46
    "
    -1.46
     lassen
    -1.45
    drá
    -1.45
    POSITIVE LOGITS
     uly
    1.75
     alemana
    1.62
    électricité
    1.55
     ぱ
    1.52
    そういえば
    1.52
    毟
    1.50
    ܞ
    1.47
     lyder
    1.46
     dirit
    1.45
    ほとん
    1.44
    Activations Density 0.008%

    No Known Activations