© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1131
    Prev
    Next
    INDEX
    Explanations

    accessing data bytes

    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
    тельное
    -0.81
     împreună
    -0.75
     îns
    -0.74
     realizarse
    -0.72
     further
    -0.69
    应该是
    -0.68
    idency
    -0.66
     Erfolg
    -0.65
     Size
    -0.65
     ภาพ
    -0.65
    POSITIVE LOGITS
     pointer
    1.53
     data
    1.45
     start
    1.28
     beginning
    1.27
     begin
    1.23
     ptr
    1.17
    Pointer
    1.15
    BEGIN
    1.14
    start
    1.13
    Begin
    1.13
    Activations Density 0.015%

    No Known Activations