© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 57450
    Prev
    Next
    INDEX
    Explanations

    begin and write

    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
    fuente
    -0.83
    PARSER
    -0.81
    publik
    -0.78
    raison
    -0.78
    Reading
    -0.77
    RELEASE
    -0.76
    lineTo
    -0.75
     kiedyś
    -0.75
     domande
    -0.75
     Bakers
    -0.74
    POSITIVE LOGITS
     start
    1.56
     begin
    1.55
     Begin
    1.41
    Begin
    1.40
     began
    1.32
     begins
    1.29
     начать
    1.28
    开始
    1.20
     started
    1.19
     begun
    1.19
    Activations Density 0.009%

    No Known Activations