© 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. 69008
    Prev
    Next
    INDEX
    Explanations

    organizations and data structures

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

    The neuron activates on words that appear as part of organization or institutional names (e.g. “Community,” “Development,” “Corp,” “Foundation,” “Center,” “Association”).

    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
     quizá
    -1.28
     aforesaid
    -1.27
     didn
    -1.22
     ersetzt
    -1.22
    ఱ
    -1.21
     wasn
    -1.20
    单独
    -1.16
     said
    -1.12
     angegeben
    -1.10
    之类的
    -1.10
    POSITIVE LOGITS
     which
    1.49
     our
    1.20
     blusas
    1.10
    ControllerAdvice
    1.09
     by
    1.08
    фран
    1.07
    ymi
    1.06
    сятся
    1.05
    zdy
    1.05
    lawan
    1.04
    Activations Density 0.081%

    No Known Activations