© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25861
    Prev
    Next
    INDEX
    Explanations

    legal filings or code

    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_34/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
    Katso
    -0.81
    湘南
    -0.79
    ӵ
    -0.77
    秋田
    -0.75
    rawtypes
    -0.75
    \\[
    -0.73
    二日
    -0.73
    ρυσ
    -0.73
     ست
    -0.72
     Mackey
    -0.72
    POSITIVE LOGITS
    ‛
    0.81
     Bedarf
    0.79
    kran
    0.76
    ånga
    0.75
    Arthur
    0.75
    हे
    0.74
    में
    0.73
    Vamos
    0.72
    zepine
    0.72
     Clapton
    0.72
    Activations Density 0.001%

    No Known Activations