© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90508
    Prev
    Next
    INDEX
    Explanations

    resignation and quitting

    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
    ͊
    -0.80
    mlink
    -0.79
     diete
    -0.78
     experimenter
    -0.76
     calibr
    -0.76
    изнь
    -0.75
     NSCoder
    -0.72
     Gera
    -0.71
     epile
    -0.71
     limon
    -0.71
    POSITIVE LOGITS
     resign
    5.75
     resignation
    5.75
     resigned
    5.56
     resigning
    4.91
    resign
    4.56
     démission
    3.63
     quit
    3.20
     quitting
    2.61
    辭
    2.53
    quit
    2.47
    Activations Density 0.114%

    No Known Activations