© 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. 34-GEMMASCOPE-RES-131K
    7. 83355
    Prev
    Next
    INDEX
    Explanations

    iterator begin

    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
     Tasche
    -0.78
    cumulative
    -0.73
     Cumulative
    -0.73
     cumulative
    -0.72
    AutoresizingMask
    -0.71
     seri
    -0.68
    累计
    -0.68
    Cumulative
    -0.68
    leni
    -0.66
     respon
    -0.65
    POSITIVE LOGITS
     begin
    1.80
    begin
    1.57
     beginning
    1.48
     begins
    1.44
     Begin
    1.35
    Begin
    1.32
     begint
    1.20
    BEGIN
    1.16
    beginning
    1.13
     BEGIN
    1.11
    Activations Density 0.039%

    No Known Activations