© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119013
    Prev
    Next
    INDEX
    Explanations

    beginnings of lists

    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
     bullet
    -0.84
     even
    -0.82
    fficiencies
    -0.81
    diğini
    -0.79
     balls
    -0.75
     Title
    -0.75
    ցված
    -0.74
     etwas
    -0.73
     ainda
    -0.73
     Rela
    -0.73
    POSITIVE LOGITS
    begin
    1.43
     begin
    1.32
     BEGIN
    1.26
     beginning
    1.24
     begins
    1.20
    Begin
    1.19
    BEGIN
    1.18
     beginnen
    1.13
     Begin
    1.12
     beginnings
    1.11
    Activations Density 0.004%

    No Known Activations