© 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. 858
    Prev
    Next
    INDEX
    Explanations

    hello world greeting variations

    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
    蘄
    -2.45
    喈
    -2.39
    bảng
    -2.38
    筇
    -2.33
    ′-
    -2.33
     admirable
    -2.22
    ">
    -2.14
    những
    -2.13
    bản
    -2.08
    跄
    -2.08
    POSITIVE LOGITS
     Then
    3.78
    .
    3.64
     Therefore
    2.55
     What
    2.42
     During
    2.39
     Roughly
    2.39
     According
    2.31
     Approximately
    2.27
    “.
    2.25
     Meanwhile
    2.25
    Activations Density 0.005%

    No Known Activations