© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79201
    Prev
    Next
    INDEX
    Explanations

    employee benefits and flexible work

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

    The neuron flags key category or heading words—especially nouns in titles or lists (e.g. department names, benefit types, or job perks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ารถ
    -0.86
    yscy
    -0.83
     estekak
    -0.82
    mientras
    -0.78
     HFILL
    -0.78
    illai
    -0.77
    tainers
    -0.77
    tainer
    -0.76
    बल
    -0.75
     Dundas
    -0.74
    POSITIVE LOGITS
     flexible
    1.48
     Flexible
    1.38
     wellness
    1.34
     flex
    1.31
    Flexible
    1.20
     gym
    1.20
     employee
    1.18
     flexibilidad
    1.18
     Flex
    1.13
    flexible
    1.13
    Activations Density 0.024%

    No Known Activations