© 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. 34-GEMMASCOPE-RES-131K
    7. 48866
    Prev
    Next
    INDEX
    Explanations

    groups of people and their context

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

    The neuron fires on words that name groups of people (e.g. “players,” “workers,” “passengers,” “employees,” “candidates,” “staff,” etc.).

    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
    ÓG
    -1.02
    冚
    -1.01
     tiempo
    -0.98
    กับ
    -0.92
    fog
    -0.92
     hacer
    -0.91
     unange
    -0.91
     wysok
    -0.90
     comidas
    -0.89
    ŚĆ
    -0.87
    POSITIVE LOGITS
     of
    2.02
     who
    1.91
     belonging
    1.73
     from
    1.42
     belong
    1.33
     belonged
    1.30
     belongs
    1.26
    groom
    1.06
     namely
    1.05
     Namely
    1.03
    Activations Density 0.074%

    No Known Activations