© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100799
    Prev
    Next
    INDEX
    Explanations

    equal opportunity employer/commission/provider

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

    The neuron activates on language around equal‐opportunity/non-discrimination and affirmative-action statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     있다
    -1.63
    jména
    -1.59
    そういえば
    -1.57
     obyvateľov
    -1.55
    还不错
    -1.52
    برو
    -1.52
     this
    -1.52
     verksamhet
    -1.51
     Umum
    -1.50
     könig
    -1.50
    POSITIVE LOGITS
    ↵
    1.87
     /
    1.54
    /
    1.40
    着她
    1.40
     “.
    1.38
    </strong>
    1.36
     tougher
    1.36
    筈
    1.35
    engeance
    1.35
     estekak
    1.34
    Activations Density 0.006%

    No Known Activations