© 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. 10-GEMMASCOPE-RES-131K
    7. 14669
    Prev
    Next
    INDEX
    Explanations

    os.path operations

    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_10/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
     listrik
    -1.86
    phère
    -1.84
    gorithm
    -1.80
    
    -1.79
    then
    -1.77
    😤
    -1.73
    赑
    -1.73
    odeficiency
    -1.72
    )"
    -1.71
    most
    -1.70
    POSITIVE LOGITS
    葙
    1.80
     sabias
    1.54
    ↵↵
    1.53
     vividly
    1.48
     boldly
    1.47
     delicately
    1.46
    窺
    1.44
     natuurlijk
    1.38
    懸命
    1.37
    dalam
    1.33
    Activations Density 0.011%

    No Known Activations