© 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. 78356
    Prev
    Next
    INDEX
    Explanations

    PE, Professional Engineer

    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
    üş
    -0.82
     BON
    -0.72
    syms
    -0.69
    pix
    -0.69
     accessed
    -0.68
     pitcher
    -0.67
     پاد
    -0.65
    partements
    -0.65
    umbra
    -0.65
     procla
    -0.65
    POSITIVE LOGITS
     PE
    1.89
    PE
    1.48
     Professional
    1.25
     P
    1.05
     registered
    1.02
    PEG
    1.00
     Engineer
    0.99
    Professional
    0.98
    Engineer
    0.97
     PEG
    0.97
    Activations Density 0.044%

    No Known Activations