© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102364
    Prev
    Next
    INDEX
    Explanations

    storage facilities or processing locations

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

    The neuron flags nouns naming formal organizations, facilities, infrastructure, or service operations (e.g. “training,” “academy,” “agency,” “storage,” “terminal,” “certification,” “zone,” “facilities”).

    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
     about
    -1.41
     again
    -1.38
     may
    -1.28
     stronger
    -1.27
     different
    -1.27
     than
    -1.27
     or
    -1.25
     メニュー
    -1.24
     empfohlen
    -1.23
     another
    -1.23
    POSITIVE LOGITS
     JpaRepository
    1.24
    pieler
    1.22
     MUNDO
    1.20
     PRAYER
    1.19
    arbonato
    1.18
    cising
    1.18
     viewDidLoad
    1.16
    🦋
    1.15
    TabStop
    1.15
    kosten
    1.15
    Activations Density 0.100%

    No Known Activations