© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111080
    Prev
    Next
    INDEX
    Explanations

    groups of people and roles

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

    The neuron spotlights plural nouns denoting groups of people (e.g. villagers, jurors, islanders).

    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
     obstruct
    -2.47
    ).
    -2.42
     eğiti
    -2.28
    ının
    -2.27
    」
    -2.19
     amaze
    -2.17
    其他的
    -2.17
     aspire
    -2.14
    larımız
    -2.06
    }
    -2.02
    POSITIVE LOGITS
    8
    3.06
    2
    3.00
    3
    2.28
    9
    2.28
    ac
    2.25
    ed
    2.25
    0
    2.23
    等我
    2.23
    how
    2.22
     the
    2.20
    Activations Density 0.002%

    No Known Activations