© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75910
    Prev
    Next
    INDEX
    Explanations

    consider hiring

    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
     száll
    -0.82
     irradiated
    -0.81
     Paras
    -0.80
    sweetalert
    -0.78
    digkeit
    -0.75
     administers
    -0.74
    zepine
    -0.74
    NOMBRE
    -0.74
    ες
    -0.74
     КО
    -0.74
    POSITIVE LOGITS
     hire
    5.66
     hired
    5.41
     hiring
    5.28
     hires
    4.41
    Hire
    4.41
    Hiring
    4.28
     Hire
    4.13
     Hiring
    4.09
    hire
    3.75
     contratar
    3.41
    Activations Density 0.105%

    No Known Activations