© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 1758
    Prev
    Next
    INDEX
    Explanations

    output buffering and flushing

    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
    omethyl
    -0.82
    ודש
    -0.78
    投げ
    -0.78
    DRAM
    -0.77
     bekam
    -0.76
     rembourse
    -0.75
    moment
    -0.74
     renforcer
    -0.74
    opatho
    -0.73
    onucle
    -0.72
    POSITIVE LOGITS
     output
    1.69
     ob
    1.49
    Output
    1.45
    ob
    1.44
     Output
    1.38
    输出
    1.34
    output
    1.27
     buffering
    1.19
    OUTPUT
    1.15
     输出
    1.15
    Activations Density 0.035%

    No Known Activations