© 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. 106889
    Prev
    Next
    INDEX
    Explanations

    testing and evaluation

    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
    																											
    -0.92
     rocas
    -0.89
    taught
    -0.89
     القرار
    -0.88
    diagnosis
    -0.85
    tracing
    -0.84
     aproximado
    -0.82
    Tracing
    -0.81
    habitude
    -0.81
     obrazov
    -0.81
    POSITIVE LOGITS
     testing
    3.77
     tests
    3.36
     test
    3.30
     tested
    2.69
    测试
    2.58
     Testing
    2.52
     laboratory
    2.42
     lab
    2.28
    Testing
    2.27
     Tests
    2.25
    Activations Density 0.054%

    No Known Activations