© 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. 78283
    Prev
    Next
    INDEX
    Explanations

    work and job satisfaction

    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
     hyö
    -0.73
    Fk
    -0.73
     homeland
    -0.69
     ধ
    -0.68
     Сара
    -0.67
    finger
    -0.66
     Parag
    -0.66
    chio
    -0.66
     Ay
    -0.65
     Pier
    -0.65
    POSITIVE LOGITS
    eramente
    0.75
     ANALYSIS
    0.72
     الأوروب
    0.71
     дії
    0.71
     प्रदेश
    0.70
    Pozri
    0.70
     Hols
    0.70
     analyzed
    0.69
    íveis
    0.68
    adz
    0.68
    Activations Density 0.031%

    No Known Activations