© 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. 22-GEMMASCOPE-RES-131K
    7. 71985
    Prev
    Next
    INDEX
    Explanations

    groups and organisations

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

    The main thing this neuron does is detect mentions of organizations, institutions, or other collective entities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     for
    -1.75
     a
    -1.34
     and
    -1.30
     which
    -1.26
     as
    -1.24
     sports
    -1.21
    ;
    -1.18
     while
    -1.17
    ’
    -1.12
    ),
    -1.11
    POSITIVE LOGITS
     montrant
    1.30
    Sü
    1.27
     mourir
    1.20
    wouldn
    1.20
    didn
    1.18
     konge
    1.16
    wasn
    1.16
    Vezi
    1.12
     laissant
    1.10
    Trois
    1.09
    Activations Density 0.192%

    No Known Activations