© 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. 22-GEMMASCOPE-RES-131K
    7. 68395
    Prev
    Next
    INDEX
    Explanations

    organization and its functions

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

    The neuron activates on words naming or classifying institutions or organizations (e.g. “company,” “firm,” “center,” “press,” “museum”).

    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
     if
    -1.43
     from
    -1.41
     without
    -1.31
     podían
    -1.31
     after
    -1.31
     querían
    -1.29
     supuestamente
    -1.29
     before
    -1.29
    AutoScaleMode
    -1.27
    になってしまう
    -1.27
    POSITIVE LOGITS
     also
    1.97
     is
    1.77
     ciutat
    1.49
     lanterna
    1.48
     boute
    1.45
     currently
    1.44
     paillettes
    1.44
    aconda
    1.43
     conster
    1.40
     venezia
    1.33
    Activations Density 0.054%

    No Known Activations