© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 148982
    Prev
    Next
    INDEX
    Explanations

    full-time employment

    np_acts-logits-general · gemini-2.5-flash-lite

    full-time, part-time job status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    3
    0.55
    ট
    0.53
    delt
    0.51
    вку
    0.50
    text
    0.49
    С
    0.48
     list
    0.47
    T
    0.47
    list
    0.47
    arom
    0.46
    POSITIVE LOGITS
     nécessité
    0.57
     باشند
    0.55
     engend
    0.55
     വേണ്ട
    0.54
     دارد
    0.54
     دارند
    0.51
     permanence
    0.50
     lessening
    0.50
     Estelle
    0.50
     باشد
    0.50
    Activations Density 0.019%

    No Known Activations