© 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. 70062
    Prev
    Next
    INDEX
    Explanations

    live action and events

    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
    medriver
    -1.75
     następnie
    -1.63
    (":");
    -1.62
     häufigsten
    -1.59
     zatem
    -1.52
    吔
    -1.49
     hyvin
    -1.48
    ttemberg
    -1.48
    喟
    -1.47
    engaruhi
    -1.46
    POSITIVE LOGITS
     was
    2.03
     isn
    1.78
    zości
    1.77
     kimdir
    1.66
    。"
    1.63
    менять
    1.61
     wasn
    1.60
     live
    1.59
    悫
    1.58
    live
    1.57
    Activations Density 0.027%

    No Known Activations