© 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. 22-GEMMASCOPE-RES-131K
    7. 26004
    Prev
    Next
    INDEX
    Explanations

    people and labor

    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_22/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
    3
    -1.37
    IRQn
    -1.30
     little
    -1.12
     small
    -1.05
     from
    -1.04
     möchten
    -1.03
    esserung
    -0.98
    مرحله
    -0.98
     値下げ
    -0.98
    quarie
    -0.98
    POSITIVE LOGITS
     manpower
    1.44
     workforce
    1.43
     personeel
    1.30
    ogos
    1.19
    蹉
    1.16
     labour
    1.11
     )}$
    1.07
    齎
    1.06
     humain
    1.06
     personnel
    1.03
    Activations Density 0.034%

    No Known Activations