© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57156
    Prev
    Next
    INDEX
    Explanations

    software performance and testing

    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
    Serve
    -0.83
    Peer
    -0.82
    کام
    -0.79
    ţele
    -0.73
    Thermo
    -0.73
     carelessness
    -0.72
    检验
    -0.72
     terrestre
    -0.72
     Ñ
    -0.70
    öre
    -0.70
    POSITIVE LOGITS
     load
    1.77
     performance
    1.62
     stress
    1.45
     Load
    1.35
    load
    1.23
     Performance
    1.20
     Stress
    1.20
    stress
    1.17
    Performance
    1.16
     regression
    1.15
    Activations Density 0.097%

    No Known Activations